payotte-mcp

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations cover the safety profile (read-only, idempotent, closed-world), and the description goes well beyond them: it names the data sources (CMHC RMS, Bank of Canada), lists the calculation assumptions (20% down, 25-year amortization, ~1%/yr taxes, $150/mo heating), and explains the two distinct output readings. This is rich behavioral disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the usage trigger, then data sources, assumptions, return shape, and limitation in dense but non-redundant sentences. Every sentence carries distinct information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-value burden and does so by describing the two readings (cash outlay vs. economic cost) and the coverage limitation. Nothing an agent needs to call or interpret the tool is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% with a single required "ville" parameter, so the schema already documents the input. The description adds nothing syntactic about the parameter, which is the correct baseline when the schema does the work.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific decision-support purpose (rent vs. buy in a Canadian city) with the exact quantities compared — CMHC two-bedroom rent vs. carrying cost of the reference home. This clearly distinguishes it from data-only siblings like taux_courants and stats_marche.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

"Call this when the user wonders whether to rent or buy in a Canadian city" gives explicit triggering context, and the trailing note about CMHC-covered metros implies when the tool will not apply. It stops short of naming a sibling alternative for related questions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already grant readOnly, idempotent, non-destructive and closed-world status, so the safety profile is fully covered. The description adds real value beyond that: it specifies the answer taxonomy, the evidentiary basis returned (statute, bar opinion, court ruling), and the practical detail of who conducts closings.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense sentence, front-loaded with the jurisdiction and the core question. Every clause carries information (classification, legal source, practitioner), though the parenthetical enumerations make it slightly heavy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description correctly compensates by describing what comes back: the requirement level, the underlying legal authority, and who typically conducts the closing. An agent has enough to know the answer shape; only pagination/format detail is absent, which is irrelevant for a single-state lookup.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Only one parameter, and the schema already documents it at 100% coverage including accepted formats (name or two-letter code). The description adds no extra parameter semantics, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific question-resource pair (attorney requirement at closing) scoped precisely to the United States and broken down by state. The enumerated answer categories (required / partly required / customary / not required) make it trivially distinguishable from siblings like closing_costs_us or title_insurance_us.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description makes clear what domain this lookup covers (US closing attorney requirements by state), which implies when it applies, but it never names an alternative tool or states a when-not condition. No prerequisite or routing guidance is given despite several adjacent US closing tools in the sibling list.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare a safe, idempotent read, so the bar is lower; the description still adds real behaviour: Belgium has no legal debt-to-income rule, the 33% share and 3.5% rate are example assumptions the caller may change, and results depend on regional purchase costs. It does not say whether unsupported municipalities raise or silently default.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the country scope and the core computation in the first sentence, with the modelling caveat second. The trailing URL/alternate-language references are padding for an agent but do establish provenance, so not a full 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, yet the description says what is returned (achievable capital and highest home price) and anchors it to a real-world calculator. Combined with 100% parameter coverage and safe read annotations, an agent has everything needed to call and interpret it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all nine parameters with defaults and ranges, making 3 the correct baseline. The description reinforces that share_of_income_pct and interest_rate_pct are adjustable example defaults and links region to purchase costs, but adds no format or constraint detail beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific computation (capital a fixed-rate loan allows, plus the maximum home price net of regional purchase costs) from a single named input, which clearly separates it from cost tools like purchase_costs_be or price tools like house_prices_be. It stops short of explicitly naming a sibling to route the agent to.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the income-in / capacity-out framing, but there is no explicit 'use this when...' or 'use X instead when...' guidance against the many neighbouring tools (purchase_costs_be, compare_regions_be, house_prices_be). The caveat about assumptions is context, not routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds substantial domain behavior beyond them: the 15%–22.5% banded rates, the 25% low-tax-jurisdiction rate, buyer withholding, resident exemption testing, and the FR1/FR2 reduction factors. The pre-1996 exclusion is a concrete boundary the structured fields do not express.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads jurisdiction and purpose, then compresses the resident/non-resident branches into a single dense sentence with no filler. It is slightly over-packed: unexplained tokens like 'FR1/FR2' and 'upper limit' cost the reader without adding selection value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 6-parameter calculator with no output schema, the description covers the key domain mechanics (rates, withholding, exemptions, cutoff year) so an agent can judge applicability. Gaps remain around the default when the optional seller is omitted and around what the calculation returns, but the core is sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 50%, and the description partially compensates by explaining the seller enum branches and the resident exemption/lower-bound mechanics that underlie reinvested and only_property. However, it never maps meaning onto the bare required fields (sale_price, purchase_cost, purchase_year) and the FR1/FR2 reference is unexplained jargon, so half the parameters remain under-specified.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource (income tax on the gain from selling a home) and immediately scopes it by jurisdiction (BRAZIL) and seller class (resident vs non-resident). An agent can distinguish it from siblings like purchase_costs_br or transfer_tax_us without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear conditions for each branch: non-residents are 'computed in full' with buyer withholding, residents get 'exemptions tested' with the FR1/FR2 reduction factors, and purchases before 1996 are explicitly out of scope. It never names a sibling alternative to use instead, so it stops short of full when/when-not routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive and openWorld=false, so safety is covered. The description adds real behavioral value by disclosing what the reader gets back (state regulators or registers, what they cover, where to check a licence) and that no Australian professional records exist in the directory.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, jurisdiction flag front-loaded, zero filler, and the caveat about missing Australian professionals placed at the end where it reads as a boundary condition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description has to carry return semantics, and it does describe the kind of content returned. For a one-parameter informational lookup with full annotation coverage, this is nearly complete; only the exact output shape is left vague.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the single 'trade' parameter is fully documented in the schema. The description merely restates the same list of trades, adding no syntax, format, or matching guidance beyond it, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource (Australian state regulators/registers for property professionals) and scopes it by trade, and the 'AUSTRALIA.' prefix separates it from check_professional_uk/in and verify_license_us. The name suggests checking a professional while the description clarifies it only points to where a licence is checked, a minor mismatch.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implies usage by enumerating the covered trades and noting 'Payotte lists no Australian professional yet', which effectively says you cannot look up a specific person here. It never names an alternative tool or states an explicit when-not beyond that.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare a safe, read-only, idempotent, closed-world lookup, so the safety profile is covered. The description adds real behavioral context beyond that: it discloses that no individual professional is named, and that the payload is regulator/register plus title meaning — a scoping disclosure the annotations cannot express.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense but front-loaded sentence: country marker first, then trades, then output content, then the negative scope clause. No filler, though the parenthetical register list is heavy and slightly slows scanning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With only two parameters, full schema coverage, and annotations carrying the safety profile, the description supplies enough to call it correctly, and the 'names no professional' clause pre-empts a likely misunderstanding about return content. An output schema is absent, but the description sketches what is returned, which is adequate here.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the 'trade' and 'language' parameters (including the fr/nl acceptance and enum) are already documented in the schema. The description reinforces the trade list but adds no syntax, format, or constraint detail beyond it, making the baseline 3 appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific scope (BELGIUM), enumerates the exact trades covered, and states the concrete output — the regulatory body or register, what the title means, and where a check is made. The country prefix and the 'names no professional' clause clearly separate it from the check_professional_XX siblings and from directory tools like trouver_professionnel_fr.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the listed trades and registers, but there is no explicit 'use this when…' or exclusion directing the agent away from verifier_titre or trouver_professionnel_fr. The agent must infer that this is a routing/regulator-lookup tool rather than a verification or directory tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely useful behavioral context about coverage (no Brazilian professionals listed; lawyers and lenders never listed), but it never explains what the response actually contains or where the 'checking' occurs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with the country scope front-loaded and no filler. The first sentence is dense but packs the trade-to-regulator mapping efficiently; the second sentence earns its place by setting coverage boundaries.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-value burden and only partially discharges it: it conveys the regulators per trade but not the shape of the answer (a body name, a URL, a lookup instruction). For a one-parameter read-only lookup that is borderline adequate, but an agent cannot predict the response.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the single 'trade' parameter is already fully documented with the same value list. The description restates the values and maps each to a regulator (CRECI, CNAI, CREA/CAU, Banco Central, OAB), but that mapping is output content rather than added input meaning, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific resource (Brazilian property professionals) and function (where a registration is checked), opening with 'BRAZIL.' so it is clearly distinguishable from the many check_professional_XX siblings. It also clarifies what the tool is not (a listing of professionals). It stops short of naming a sibling tool, and the deliverable ('where the reader checks a registration') is phrased indirectly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The trade list and the note that Payotte 'lists no Brazilian professional yet, and never lists lawyers or lenders' imply when the tool applies and its coverage limits. However, no alternative tool is named and no explicit when-to-use/when-not instruction is given relative to siblings like verify_license_us or trouver_professionnel_fr.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (read-only, idempotent, non-destructive, closed-world). Beyond that, the description adds genuinely useful context an agent can't get elsewhere: which register (or lack of one) applies per trade, and the firm-listing/notary limitation. It does not describe the return shape, keeping it shy of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One dense sentence, front-loaded with the country scope so the agent screens on it immediately. The parenthetical regulatory references are compact rather than wasteful, though the sentence carries a lot of parenthetical load.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter, read-only lookup with no output schema, the description supplies the country scope, the covered trades, and the notable limitations. Nothing essential for correct invocation is missing, though it could state more explicitly how the result should be used.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema already enumerates the five acceptable trade values, so the description's trade list largely repeats it. The § references and register names add marginal interpretive value, but the parameter itself needs no further explanation. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — telling the reader where to verify a German property professional — and maps it to the exact five trades it covers, each with its regulatory hook (§ 34c GewO, § 34i DIHK, public appointment, state chambers, public office). The leading "GERMANY" plus the trade list cleanly separates it from its check_professional_XX siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear usage context by enumerating which trades it applies to and, importantly, sets exclusions: no German firm is currently listed and notaries are never covered. It stops short of explicitly naming alternative siblings (e.g. check_professional_uk or trouver_expert) or the when-not-to-use case, so it is clear but not fully routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely new scope context — that this returns regulator/register information rather than professional listings, and that lawyers are never listed — which prevents a wrong expectation about the output.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the country scope, and the trade→regulator mapping is packed densely with no filler. The elliptical 'where the reader checks' phrasing costs a little clarity but nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description must carry the return contract; it conveys that the answer is regulator/register guidance per trade, which is adequate for a one-parameter lookup. It stops short of saying whether concrete body names or URLs are returned, a minor gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for the single required 'trade' parameter, so the baseline would be 3. The description goes beyond the schema by mapping each trade value to its specific regulator (regional registers, Banco de España, colegios, bar associations), which clarifies what each accepted value actually retrieves.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific resource (the regulator/register to check for each Spanish property trade) and enumerates the trades it covers, so an agent knows exactly what it returns. It signals 'SPAIN' but never names the sibling check_professional_au/br/in/mx/uk tools it is parallel to, leaving the country differentiation implicit in the name alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied: use it to find which body regulates a given Spanish trade. The caveat 'Payotte lists no Spanish professional yet and never lists lawyers' is a useful when-not-to-expect-listing signal, but it never names an alternative (e.g. trouver_expert, contacter_expert) or states when to prefer those over this tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish the safe read profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false). The description adds a genuine dataset caveat — no Indian professionals are currently listed and lawyers are never listed — which is useful behavioural context beyond the annotations. It does not say whether a regulator link, name, or contact detail is produced, so disclosure remains partial.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the country qualifier and then a compact value-to-regulator list — no padding. The trailing 'Payotte' sentence introduces an unglossed brand name that slightly muddies the close.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter, read-only lookup with no output schema, the description should make clear what comes back (regulator name, verification URL, procedure). It only gestures at 'where the reader checks a registration', leaving the response shape ambiguous, though parameter meaning and scope exclusions are covered.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the sole enum-less 'trade' parameter is already documented with the same five values. The description pairs each value with its regulator (agent→state RERA, valuer→IBBI, etc.), which adds meaning about what a given value yields, but it does not help with spelling, casing, or accepted synonyms for the parameter. Baseline 3 is warranted.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific domain and resource: an India-only mapping from property profession (agent, valuer, architect, lender, lawyer) to the body that regulates it (state RERA, IBBI, Council of Architecture, RBI, State Bar Council). The 'INDIA.' prefix cleanly separates it from check_professional_au and check_professional_uk. The phrasing 'where the reader checks a registration' is slightly oblique about what is actually returned, keeping it from a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage (pick a trade to learn its regulator) and hedges scope with 'Payotte lists no Indian professional yet and never lists lawyers', which is a soft exclusion about expected results. It never states when to call this instead of siblings such as guide_in, verify_license_us, or trouver_professionnel_fr, so routing is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, openWorld=false and non-destructive, so the safety bar is low. The description adds genuinely new behavior context: the tool points to external registers rather than listing firms, and it will never return notaries. That is exactly the kind of coverage limitation an agent needs before calling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense paragraph front-loaded with the country scoping and closing with the coverage caveat. Almost every clause earns its place, though the parenthetical register lists make it read more like reference notes than a front-loaded summary.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter, no-output-schema lookup tool, the description conveys both what will be returned (where to check, per trade) and what will not (no firm listings, no notaries). Combined with the annotations, an agent has enough to invoke it correctly; only explicit sibling routing is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With one parameter and 100% schema description coverage, the schema already documents 'trade' and its five values. The description restates those values and maps each to its register (Registro Imprese/REA, OAM, geometri, Albo Unico), which is modest added meaning, but nothing about format or validation is supplied beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a concrete resource (the regulator/register for each Italian property trade) and scopes itself to Italy with the 'ITALY.' prefix, which separates it from the check_professional_* sibling family. The action is expressed indirectly ('where the reader checks') rather than as a crisp verb, but an agent can still tell what the tool returns.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied: use this when you need the Italian regulator/register for one of five trades. The closing note that 'Payotte lists no Italian firm yet and never lists notaries' functions as a partial when-not signal, but there is no explicit routing to alternatives such as trouver_professionnel_fr or verify_license_us.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered. The description adds a genuinely non-obvious behavioral fact: it returns regulator references and never produces listings for notaries or lawyers. It stops short of describing the return shape (names vs. URLs), so not a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with 'MEXICO' and the trade-to-regulator mapping. Efficient, though the closing clause about notaries/lawyers is wedged in and could be cleaner.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter, no-output-schema reference tool the description covers who regulates each trade and the important negative (no listings). It does not describe the form of the answer, a minor gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and there is only one parameter, so the schema already carries the trade description. The description restates the same five trade values, adding no format or validation detail beyond the schema; baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource (regulator/where-to-check for each Mexican property trade) with an explicit country marker, so it is clearly distinguishable from the sibling check_professional_au/br/es/in/uk tools. The phrasing 'where the reader checks' is slightly indirect about what the tool actually returns, keeping it short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The sentence 'Payotte lists no Mexican professional yet and never lists notaries or lawyers' usefully signals that this is a regulator-reference tool rather than a directory lookup. However, no alternative tool is named for actually finding a professional (e.g. trouver_expert/contacter_expert), so usage is implied rather than explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety and closed-world profile is fully covered structurally. The description adds content-scope context by naming the specific registers returned (FCA Register, SRA, CLC, Law Society, RICS, redress schemes), but says nothing about freshness, whether it reflects live registration status, or result format.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the jurisdiction and packs the core content into one dense sentence. The second sentence about Payotte's one-firm-per-trade coverage in 20 UK areas is somewhat tangential to the tool's regulatory purpose but does bound the data source, so it earns partial keep.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With one required parameter, 100% schema coverage and no output schema, the description does the needed work by enumerating what the reader gets back (regulator, coverage, where to check). It is adequately complete; the only gap is not clarifying the return shape (e.g. a per-trade list of bodies) now that no output schema exists.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%: the single 'trade' parameter is documented in the schema with the same enumerable list the description repeats. There is no enum constraint, so the description's restatement of valid trades is redundant rather than additive. Baseline 3 is appropriate when the schema carries the parameter documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States the resource (UK property professional regulation), the trades covered (estate agent, mortgage adviser, conveyancer, surveyor, valuer) and the output content (regulator/register, coverage, where to check). The 'check_professional_X' naming pattern plus the UNITED KINGDOM prefix distinguishes it from the AU/BE/BR/DE/ES/IN/IT/MX siblings. Minor ambiguity: it reads as a static regulator lookup rather than verification of a named individual, and the verb 'check' is not fully disambiguated from that sense.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the country in the name and the trade-scoped parameter, but the description never states when to use this versus alternatives such as verify_license_us or trouver_professionnel_fr, nor any exclusions. The trailing sentence about Payotte listings is scope information rather than routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish readOnly/idempotent/non-destructive, so the bar is lower, and the description still adds real behavior: the computation base rule (higher of price vs. appraisal/cadastral value), the 'not computed' fallback for unsupported municipalities, and the notary-fee exclusion. It does not describe the shape of the returned figure, which keeps it from a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the country and the verb, then adds scope and caveats. The long illustrative municipality list costs some space, but it genuinely helps the agent match the free-text municipality parameter, so it mostly earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the burden of explaining returns, and it does say the tool yields a computed tax/recording figure or 'not computed'. Coverage limits, base rule and exclusions are all present; only the exact output fields are left unspecified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and all three parameters are documented there, so the baseline is 3. The description restates the base-value rule (higher of price and appraisal/cadastral value), which is useful context but largely duplicates the schema's own note that the value applies 'if higher than the price'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (computes) and specific resources (Mexican property acquisition tax ISAI/ISABI/ISTD plus the state deed-recording fee) with an explicit geographic scope of 54 municipalities. An agent can distinguish this from closing_costs_us, purchase_costs_es or frais_notaire_fr without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear context: coverage of 54 named municipalities, an explicit out-of-scope signal ('others return "not computed" with no figure'), and an exclusion ('Notary fees are not computed') that implicitly routes notary questions elsewhere. It stops short of naming an alternative tool explicitly, so it is a 4 rather than a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world). The description adds genuinely non-derivable behavior: it discloses that it does not fabricate averages and explicitly reports when no official typical total exists, and that it includes a worked example and payer attribution. Return format/pagination is not described, keeping it at 4 rather than 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three compact sentences with the jurisdiction front-loaded and no filler. The final sentence about not inventing averages earns its place as a trust signal, though the enumeration of covered cost types is somewhat list-heavy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter, closed-world lookup with no output schema, the description conveys scope, included cost categories, payer attribution, and the handling of missing official data. Only minor gaps remain (e.g., that the response is a fixed statutory dataset rather than a live computation).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the single `state` parameter is fully documented (name or two-letter code) in the schema itself. The description adds no extra constraint or format guidance beyond what the schema already states, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific resource (US state-mandated closing costs) and enumerates exactly what is covered: transfer and mortgage taxes, recording fees, regulated title premiums, plus who pays each. That scoping implicitly separates it from narrower siblings like transfer_tax_us and title_insurance_us, but no sibling is named explicitly, so it falls short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: an agent can infer this applies when a US state's closing costs are needed. There is no statement of when NOT to use it, nor a pointer to the narrower siblings (transfer_tax_us, title_insurance_us, state_overview_us) for single-component questions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is fully covered without the description. The text adds only the scope of the answer (three classification buckets), with no note on data vintage, jurisdiction limits beyond 'UNITED STATES', or lookup behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence, front-loaded with the jurisdiction marker 'UNITED STATES.', then the classification and its practical meaning. Every clause earns its place with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter, read-only lookup with no output schema needed and annotations covering safety, the description gives an agent enough to invoke it correctly. A brief note on the return shape (the three regimes) is present, though nothing addresses staleness or edge cases like non-married buyers.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There is a single required parameter with 100% schema description coverage, including accepted formats (name or two-letter code) and examples. The description adds nothing about the parameter, so the schema does the work and baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific resource and the exact classification it returns (community property / opt-in / common law), plus the practical domain (titling a home as a married couple). It is distinguishable from neighbors like property_tax_us or title_insurance_us, but it never names a sibling to route against.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied through the phrase 'for buying and titling a home as a married couple', which signals the marital-property context. There is no explicit when-to-use, when-not-to-use, or pointer to a related tool such as compare_states_us or state_overview_us.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare a read-only, idempotent, non-destructive, closed-world operation, so safety is well covered. The description adds that the comparison is sourced from Payotte's guides and their official sources, which gives useful provenance context. It says nothing about freshness, pagination, or output shape, but with this annotation profile the bar is lower.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense sentence that front-loads the scope (UNITED KINGDOM, one rule across four nations) and then enumerates topics. It is compact and waste-free, though the long parenthetical is slightly heavy for a description that chiefly restates the enum.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter, annotated, read-only comparison tool, the description covers scope, source, and topic coverage adequately. The absence of an output schema leaves the return shape undocumented, but that is minor given the tool's straightforward nature.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the enum fully enumerates the eight allowed topics, so the schema carries the parameter contract. The description's parenthetical list of topics mirrors the enum exactly, adding no new semantics beyond confirmation. Baseline 4 is appropriate when the schema is this complete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (compared) and resource (one rule across the four UK nations), and names the eight topics it can compare. The sibling 'compare_states_*' tools cover other countries, and 'purchase_tax_uk' is a single-topic cousin – an agent can distinguish this cross-nation comparison tool immediately.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use it (when you need a rule compared across all four UK nations) but gives no explicit when-not-to-use or alternative routing. With 'purchase_tax_uk' present as a sibling, a sentence on when to prefer this cross-nation view over the single-rule tool would have helped.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already establish the safe read-only, idempotent, non-open-world profile, so the remaining burden is low. The description adds genuinely useful behavioral context beyond the structured fields: it identifies Statbel as the data source and explains that registration duties are set regionally while the notary tariff is federal, which tells the agent why results differ across Regions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences: the country tag is front-loaded, the output enumeration follows immediately, and the closing clause about regional vs federal competences earns its place by explaining result variation. No filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema present, the description carries the return-value burden and does so by listing every output field, and all three inputs are fully documented in the schema. It stops short of noting whether figures are indicative estimates or how current the Statbel price data is, a minor gap for a cost calculator.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% (price default 300,000 EUR, sole_home default true, flemish_core_city scoped to Flanders/periphery), so the schema already carries all parameter meaning. The description adds no formats, ranges, or interactions between parameters, making the baseline of 3 appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb (compare) and resource (the same purchase across Brussels-Capital, Wallonia and Flanders), then enumerates the exact comparison outputs: registration duty, notary, other costs, total, share of price, and each Region's median house/apartment price. This distinguishes it from single-jurisdiction siblings such as purchase_costs_be and house_prices_be without ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the comparative framing, but the description never states when to reach for this versus purchase_costs_be (single-region cost detail) or house_prices_be (price data only), nor does it state any exclusions. An agent can infer the fit but is given no explicit routing rule.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is fully covered. The description adds one genuinely useful behavioral constraint — 'One rule' per call, i.e. the tool compares a single topic at a time — plus the 19-region scope, but says nothing about the returned comparison format.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence led by 'SPAIN.' with the scope stated before the topic list. It is efficient, though the enumeration of all eight topics duplicates the schema enum rather than condensing it.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter, read-only comparison tool this is essentially sufficient: it names the country, the region count, and the available topics, and annotations carry the safety profile. With no output schema present, the return shape (a per-region table) is only hinted at via the schema's 'Topic of the table', which is a minor gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the topic parameter is a fully enumerated enum, so the schema does the documentation work. The description merely re-lists the same eight enum values verbatim, adding no syntax, default, or selection guidance beyond what the schema already provides; baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('compared'), resource ('one rule') and scope ('across the 19 regions'), and pins the country as Spain. It is clearly distinguishable from guide_es or house_prices_es, though it never names a sibling or contrast explicitly, so the differentiation is implicit rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied rather than explained: an agent can infer you pass a single topic and receive a cross-region comparison. There is no when-to-use/when-not guidance and no mention of alternatives such as guide_es or house_prices_es, which cover overlapping Spanish content.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is fully covered. The description adds the fixed scope of the result (all 20 regions, a single measure), which is useful, but it discloses nothing about shape, ordering, or size of the returned comparison.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short fragments, front-loaded with the country and followed immediately by the scope. Every token carries information; only the telegraphic 'ITALY.' prefix is slightly cryptic.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter, enum-constrained read tool with no output schema, the description conveys the country, the unit of comparison, and the measure, which is enough to invoke correctly. Annotations handle the safety side, so nothing essential is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the single parameter is a one-value enum, so the schema carries full meaning. The description merely restates the same enum value ('home-sales') without adding format, constraints, or examples. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

It names a specific verb ('compared'), resource ('the 20 regions'), geography ('ITALY'), and the single measure in scope ('home-sales'). This clearly separates it from compare_regions_be/es and the other national comparison siblings, though it never explicitly contrasts itself with home_sales_it, which covers the same data without regional breakdown.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use statement and no named alternative. The scope ('across the 20 regions') implies the comparison use case, but an agent gets no guidance on when to pick this over home_sales_it or compare_nations_uk. Guidance here is entirely inferred.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds useful provenance ('from Payotte's guides and their official sources') and clarifies that the scope is one rule across all states, but says nothing about output format or currency of the data.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with the jurisdiction marker first and the topic scope immediately after; every clause carries information. Slightly dense parenthetical enumeration, but nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter, no-output-schema tool the description is nearly sufficient: it identifies the jurisdiction, the unit of comparison, the topic domain, and the data source. It omits only return-shape and freshness details, which are minor given the simple enum-driven input.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the enum already enumerates all eight valid topics. The description merely repeats that same list, adding no syntax or interpretation beyond what the schema provides, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (compared) and resource (one property rule across Australian states and territories), and enumerates the eight comparable topics. The 'AUSTRALIA.' prefix implicitly separates it from compare_states_us/uk/in, but no sibling is named explicitly, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no when-to-use, when-not-to-use, or alternative routing. An agent must infer that this is the state-comparison tool versus the single-state tools (purchase_duty_au, guide_au) or the cross-country comparators purely from the name and topic list.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive, and closed-world behavior, so the safety profile is covered. The description adds that the output is a single table spanning 27 federative units, which is useful context, but says nothing about units, formatting, or whether filtering is possible.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with the country marker first and the topic list trailing. It is tight, though re-enumerating the six topics already present in the schema is mildly redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter read-only tool with no output schema, the description is minimally adequate: an agent knows what topics exist and that results are one table across 27 units. It omits what columns/units the table returns and whether any filtering or pagination applies, leaving some gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the single enum parameter is fully documented in the schema. The description merely re-lists the same six enum values, adding no syntax, default, or interpretation beyond what the schema already provides, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the resource (Brazilian property costs/figures) and scope (one table across the 27 federative units), and the leading "BRAZIL." tag distinguishes it from the many compare_states_* siblings. It stops short of an explicit verb like "compare", relying on the title, but the resource and country are unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to choose this over alternatives such as purchase_costs_br, guide_br, or the other compare_states_* tools. The reader can infer it is a cross-state comparison, but no condition, exclusion, or routing to a sibling is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare the full safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false, openWorldHint=false), so the burden is low. The description adds no behavioral context beyond that — no note on result shape, ordering, or state coverage gaps — so it neither helps nor contradicts.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Very short and front-loaded, with the country identifier first and the compared topics after. The one-word 'GERMANY.' fragment is slightly awkward, but every token carries scope information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter, read-only, closed-world comparison tool with no output schema, the description covers country, unit of comparison (states), and valid topics. It leaves the return format implicit, but the agent has enough to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the single 'topic' parameter is an enum with all five values documented. The description restates exactly those five topics, adding no meaning beyond the enum, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb and resource — one rule compared across the 16 German states — and anchors the country with 'GERMANY', which cleanly separates it from sibling compare_states_au/br/in/mx/us and compare_regions_be/es/it. An agent can identify the tool from the description alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: pick one of the five listed rules and see how the states differ. It never states when to prefer this over siblings like guide_de, rents_de, or purchase_costs_de, nor any exclusions or prerequisites. Adequate scope signalling, but no explicit when-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds one genuinely useful behavioral fact beyond that: the comparison is scoped to states 'whose official rates Payotte read,' i.e., a coverage limitation. It says nothing about the table's shape, row granularity, or how states lacking data are handled.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with no filler, leading with jurisdiction and topic scope. The unexplained proper noun 'Payotte' costs it a point, since an agent cannot tell whether that is the data vendor or a filter, but nothing is padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter, read-only lookup with full schema coverage and no output schema, the description supplies the essentials: jurisdiction, verb, and the two permitted topics. The data-coverage caveat is a nice touch. Return format need not be explained absent an output schema, though row-level granularity would help.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% with a single enum parameter, so the schema already does the heavy lifting. The description restates the two enum values ('purchase-duty', 'women-buyer-rates') but adds no meaning beyond them, such as units, rate basis, or what a women-buyer-rate comparison actually contains. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (compared) plus the resource (one Indian property rule) and enumerates the exact topics covered (purchase-duty, women-buyer-rates). This clearly separates it from single-jurisdiction siblings like stamp_duty_in, though it never names an alternative outright. The leading 'INDIA' makes jurisdiction unambiguous in a list crowded with US/AU/UK/French tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit guidance on when to pick this over stamp_duty_in, guide_in, or the other compare_states_* tools. Usage can only be inferred from the enumerated topics, and the description never states what a caller should already know (e.g., that it returns a cross-state table rather than a single-state rate).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so the safety profile is fully covered elsewhere. The description adds the useful constraint that output is a single rule/figure compared across states (i.e., one topic per call), but says nothing about the returned table's shape or coverage, so it only modestly exceeds the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single tight sentence, front-loaded with the jurisdiction tag, with no filler. The topic enumeration duplicates the schema enum, which is a minor redundancy but also aids routing at a glance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter, read-only lookup with complete annotations, the description covers what the tool does and the scope of each call. There is no output schema, so a brief note on the returned comparison's format would have closed the remaining gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the enum already lists all seven allowed values, so the schema fully documents the single parameter. The description merely repeats that same value list and adds no syntax, default, or interpretation guidance beyond it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (compared) and resource (one rule or figure across the states) and pins the jurisdiction with 'MEXICO.', which cleanly separates it from the many compare_states_* siblings for other countries. The enumerated topics further disambiguate what can be compared.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied rather than stated: listing the seven comparable topics tells the agent what inputs are valid, but there is no explicit when-to-use guidance, no mention of when to prefer this over guide_mx, home_prices_mx, or closing_costs_mx, and no exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already establish the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), so the bar is lower. The description still adds meaningful behavior: it discloses that output is a categorization of states under a single topic, and decodes what each category actually represents (e.g., transfer-tax = states with no transfer tax, foreclosure = judicial vs non-judicial). It stops short of describing grouping/order of the returned state lists.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the jurisdiction, then a single dense sentence enumerating topics and their meanings, then a one-line usage cue. Minimal waste; the parenthetical glosses on each enum value are the only slight repetition against the schema, but they carry new information rather than restating enum strings.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

One enum parameter, no output schema, and strong annotation coverage — the description is nearly complete for this tool because it defines every topic option and the question type it answers. The only missing piece is any hint about the response shape (e.g., one list of states per side of the classification), which is minor given the absence of an output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the enum itself lists the five topics, so baseline would be 3. The description goes beyond the schema by explaining the semantic meaning of each enum value — exactly what the enum names alone do not convey — which is genuine added value over the raw parameter definition.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (lists) and resource (the states in each category for one topic), and front-loads the jurisdiction (UNITED STATES) which cleanly separates it from the sibling compare_states_au, compare_states_in, and compare_nations_uk tools. An agent can tell what it returns and for which country without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The closing 'Use for "which states…" questions' gives a clear when-to-use cue tied to a recognizable question shape. It does not, however, mention the per-topic sibling deep dives (transfer_tax_us, attorney_at_closing_us, foreclosure_us, seller_disclosure_us, community_property_us), so the agent gets context but no explicit routing between this cross-state comparison and those single-topic tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses the non-obvious double opt-in flow: it does NOT email the expert, instead sends a confirmation link to the user (valid 48h), only reaching the expert after the click, and Payotte keeps no copy. This goes well beyond the annotations and covers the key behavioral surprise of the tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the ONLY-when trigger, then the opt-in mechanics, then a compact numbered pre-call checklist. Despite its length, nearly every sentence carries distinct operational information and none is redundant with the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 9-parameter mutation tool with no output schema, the description covers trigger, mechanism, prerequisites, safety constraints, and what the user should expect afterward. It is nearly complete; only field-level edge cases (e.g., validation failures) are left to the schema's own constraints.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so a baseline of 3 applies, but the description adds real semantics: it explains the ordering of collected inputs, the consentement=true gating rule, and the warning never to invent contact details. It stops short of clarifying field-level formats, which the schema already handles.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a precise verb+resource (contact a verified Payotte-listed professional) and immediately distinguishes its trigger from siblings by requiring an explicit user request and pointing to trouver_expert as a prerequisite lookup. An agent can tell exactly what this tool does and when it applies without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use (only on explicit user request to contact/request a quote), names the alternative (trouver_expert to select the expert first), and lays out a numbered precondition sequence ending in consentement=true. No usage inference is left to the agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare the safe read-only, idempotent, non-destructive profile, so the burden is lighter. The description adds real behavioral value: it discloses the computation method, that it subtracts the filing fee when known, that it also shows the upward cost, and that it will not guess municipal rates.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The trigger is front-loaded and every sentence carries information, though the parenthetical 'because a review can raise the value' and the closing instruction slightly pad an otherwise efficient passage.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description reasonably describes what the tool returns (savings and upside cost) and the inputs it depends on. It is complete enough to call correctly, though it does not detail the output structure or units of the returned figures.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds meaning beyond the schema by clarifying that 'baisse' is a hypothetical chosen by the user rather than a predicted value, and that the tax rate must come from the user's tax bill.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific quantitative job — multiplying a hypothetical assessment reduction by the tax rate over remaining roll years and subtracting the filing fee — which is distinct from siblings like frais_revision or taux_courants. An agent can tell exactly what resource and output this tool produces.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states the exact trigger ('when the user asks how much they could save on property taxes if their assessment went down, or whether contesting is worth the fee'), covering both the savings and cost-benefit use cases. It also specifies the prerequisite action of asking the user for their tax rate rather than guessing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish readOnly/idempotent/non-destructive, and the description adds real behavioral context beyond them: it discloses that only open rolls are read, that no owner names are returned, that figures are comparisons rather than an opinion of value, and that ballpark market value is emitted only where an official source permits it.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the trigger sentence, then a dense enumeration of returned data and coverage. Every sentence carries information, though the long municipality list is bulky; still, no wasted filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the full burden and does so: it enumerates the return payload (assessed value, roll years, market date, change from previous roll, rank among similar properties, ballpark market value, appeal deadline) and states the coverage boundaries. An agent knows exactly what to expect.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 75%, so most parameters are self-documented, but the description adds meaning for the province parameter by enumerating the covered jurisdictions (Quebec, NS, NB, MB, AB cities) and for market value by tying it to the source per jurisdiction. The lang enum is left unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource (reads open assessment rolls for a single address) and precisely scopes it to homeowner questions about assessed value, over-assessment, or home worth. It clearly distinguishes itself from portfolio/market tools like stats_marche or taxe_bienvenue_adresse by being address-specific.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit trigger condition ("Call this when a homeowner asks about the assessed value of a SPECIFIC address...") plus an exclusions clause ("Other provinces have no open roll by address"). It does not name sibling tools as alternatives, so it stops short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's remaining burden is lighter. It usefully adds that an empty query returns the full list, but says nothing about return format, result count, or ranking that an agent might need.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the country scope and the core action, and the trailing topic list, while long, is functional keyword surface for query matching. Slightly list-heavy, but nothing is redundant with the title or schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only, closed-world search tool with one optional parameter, no output schema, and safety fully covered by annotations, the description supplies the topic vocabulary and empty-query behavior needed to call it correctly. Only the omission of any alternative-tool routing keeps it from being complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema coverage on a single optional 'query' parameter, the schema already documents the argument. The topic list in the description reinforces what kinds of values match, but adds no syntax or format guidance beyond the schema's own example.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Finds Payotte's federal guides') and scopes it precisely as rules that apply in every state, immediately distinguishing it from state_overview_us and the country-specific guide_au/in/uk siblings. An agent can identify the tool's remit without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The topic enumeration plus the 'federal (rules that apply in every state)' scoping gives clear context for when this tool applies, and 'Empty query = full list' specifies the no-argument behavior. However, it never names an alternative (e.g. state_overview_us for state-specific rules), so routing is left partially to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare this a safe read-only, idempotent, non-open-world lookup, so the safety profile is covered. The description then adds real value beyond the annotations: data provenance (Payotte, MAMH open data; official sources for other provinces), the caveat that the assessment notice prevails, and the exact rule set returned.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The trigger condition is front-loaded in the first sentence, followed by return values, provenance, and scope limits. It is somewhat dense across three sentences, but each clause carries distinct information and none is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description fully compensates by enumerating the returned fields (roll years, reference date, general deadline, late-notice and mid-roll rules). For a zero-required-parameter lookup tool this is complete enough for an agent to call and interpret it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all three parameters (`province`, `date_avis`, `municipalite`) are already documented, including the late-notice rule link for `date_avis`. The description reinforces the Quebec default and the province-code behavior but adds little syntax or format detail the schema does not already carry — the expected baseline of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource — determining the deadline window to contest a property assessment — and enumerates exactly what it returns (roll years, reference date, general deadline, late-notice rule, mid-roll rules). The closing line 'Does not say whether an assessment is too high' cleanly separates it from valuation/estimation siblings like estimer_economie.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit trigger conditions ('when the user asks until when they can contest...which assessment roll is in force, when the next roll comes'), covers the out-of-Quebec case via `province`, and states a boundary (not for judging whether an assessment is too high). It stops short of naming an alternative sibling tool for that out-of-scope question.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotent=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuine content disclosure beyond that: it tells the agent the answer will contain recording offices, free name sources, official statewide portals, and statutory deed-copy fees, which sets expectations for the return payload despite there being no output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the jurisdiction marker and then a tight enumeration of the four things returned. One sentence, no wasted preamble, though the closing clause 'the fee for a copy of a deed when the statute was read' is slightly garbled and costs a bit of clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With one fully documented parameter, no output schema, and read-only annotations, the description supplies what an agent needs: jurisdiction scope and the composition of the answer. Only the absence of any sibling routing or 'when not to use' note keeps it below a 5.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the single 'state' parameter is fully documented with name/code examples, so the schema does the heavy lifting. The description only echoes the 'state or DC' scope; it adds no format or edge-case guidance beyond the schema, which is the baseline-3 case.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a concrete subject (property ownership lookup in the US) and enumerates exactly what the tool returns: recording office, free assessor parcel search, statewide online search, and deed-copy fee. It is clear this is a reference/guide answer rather than a live lookup, but it does not distinguish itself from adjacent siblings such as state_overview_us or verify_license_us.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the 'How to find out who owns a property' framing and the 'UNITED STATES' scope marker, but there is no explicit when-to-use statement, no preconditions, and no routing to alternatives for related questions (title verification, deed transfer, state overviews).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered structurally. The description adds the geographic scoping ('UNITED STATES') and notes results include official links, which is modest extra context. It does not disclose anything about freshness of the data, rate limits, or whether state-level program availability varies over time.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence, front-loaded with the scope marker 'UNITED STATES' followed by the resource and its contents. It is dense but every clause maps to actual content the tool returns. Slightly list-heavy but no filler sentences.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, and the description compensates well by enumerating the categories of information returned (loans, DPA, MCCs, income limits, education requirement, official links). Combined with the fully documented single parameter and the read-only annotations, an agent has enough to call it correctly. It could be more complete about territory/DC coverage and data currency.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Only one parameter and schema description coverage is 100% — the schema already documents that 'state' accepts any of the 50 states by name or two-letter code with examples. The description adds nothing beyond what the schema provides, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a concrete resource (state housing finance agency first-time buyer programs) and enumerates the specific contents: loans, down payment assistance, mortgage credit certificates, income limits, education requirement, official links. That is far more specific than a tautology and clearly distinguishes it from generic siblings like state_overview_us or federal_guide_us. It never explicitly names those siblings as alternatives, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to use this tool versus federal_guide_us, state_overview_us, or the various house_prices/foreclosure tools in the sibling list. No exclusions either — an agent cannot tell whether this is only for first-time buyers, only for US states, or how it differs from the federal-level guide. Usage is implied by the name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare this as a read-only, idempotent, non-destructive, closed-world lookup, so the safety profile is covered. The description adds useful content-scope context (which foreclosure aspects are included), but says nothing about freshness, jurisdiction limits beyond 'US', or whether data is ever trimmed — acceptable but not rich for a pure reference tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single tight sentence with no redundancy, and the jurisdiction is front-loaded. The all-caps 'UNITED STATES.' fragment is a slightly awkward stylistic lead-in, but it does signal scope immediately.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter lookup with no output schema, the description carries the burden of stating what comes back — and it does, enumerating the five content areas. Safety is handled by annotations, so nothing critical is missing; only usage routing and data-freshness notes are absent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There is a single parameter with 100% schema description coverage documenting accepted names and two-letter codes, so the baseline is 3. The description's 'by state' phrasing confirms the axis of lookup but adds no format or edge-case detail beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific resource — the US state-level foreclosure process — and enumerates the exact facets returned (judicial vs. trustee sale, timeline, redemption, deficiency judgments, mediation). That is far more informative than the title alone, though it never explicitly distinguishes itself from the adjacent US reference tools such as state_overview_us.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to reach for this tool versus its many US siblings (state_overview_us, federal_guide_us, seller_disclosure_us, etc.), and no prerequisites or exclusions. The agent must infer usage from the topic alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish the safe read-only, idempotent, closed-world profile, and the description adds real substance on top: the exact duty components included, the 2025 rate increase and first-time-buyer exemption, and the explicit exclusion of unregulated disbursements. It does not cover auth needs or return shape, but the scope disclosure is well beyond what the annotations carry.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the country and the call trigger, then the computation basis and parameter modes. Dense and mostly earned, though the component enumeration in the middle sentence is long enough that it slightly buries the usage instruction.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-value burden, and listing the computed components (duty, communal tax, collection fee, CSI, émoluments with VAT) effectively implies the breakdown. It stops short of saying whether a total is returned or how the estimate is presented.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, but the description adds cross-parameter semantics the schema does not: 'ancien' is the default and requires a département, while 'neuf' uses a reduced rate. That dependency and default behavior are genuinely useful additions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: computing the 'frais de notaire' (transfer duties + notary fees) for a French property purchase. The country scoping and the explicit list of computed components make it clearly distinct from siblings like taxe_mutation or closing_costs_us without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a precise trigger ('Call this when the user wants the frais de notaire on a property purchase in France') and pins the market with 'FRANCE'. It does not name sibling alternatives or state when NOT to use it, so it stops short of the explicit routing a 5 requires.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only cover the safety profile; the description adds the substantive behavior: the fee is read from the municipality's official page, coverage is limited to Montréal, Québec City, Laval and Gatineau for now, the legal TAQ cap is included, and other Quebec municipalities return 'not collected' rather than an estimate. This is exactly the operational context annotations cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four sentences, front-loaded with the trigger, and each one carries distinct information (when to call, what is returned and from where, fallback behavior, province routing). No filler or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description does the work of explaining the return value ('not collected', published provincial fees, TAQ cap) and coverage limits. It is nearly complete, though it never states behavior when all optional parameters are omitted or what happens for a Quebec municipality outside the four supported ones.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description goes further by explaining that `province` should be passed for non-Quebec jurisdictions and that `valeur` is the assessed roll value. It adds real usage semantics on top of the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a precise verb and resource (returns the filing fee for a request for review of a property assessment), plus the geographic scope (Quebec, with four named municipalities). It does not explicitly distinguish itself from close siblings like fenetre_revision or taxe_mutation, so an agent must still infer the boundary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives an explicit trigger ('Call this when the user asks how much it costs to file a request for review') and routes the agent to the province parameter for non-Quebec cases. It never names a sibling tool or states when to prefer an alternative, so the routing guidance stops just short of the top level.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world corpus). The description adds genuinely new behavioral detail beyond them: the response is a self-contained short answer with a check date and URL, which tells the agent what it will receive and that answers carry a freshness marker.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence with the country scope front-loaded ("AUSTRALIA.") followed by what is found and what is returned. No filler, though the enumeration of covered topics makes it denser than necessary.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description compensates by describing the return payload (short answer, check date, URL), and annotations supply the safety/closed-world context. For a one-parameter lookup tool, an agent has everything needed to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the single query parameter is already documented with examples, so the schema carries the load. The description reinforces that the input can be a question or keywords, but adds no syntax, format, or matching-behavior detail beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ("Finds the Payotte guide") plus the exact domain covered (buying, financing, selling, renting, owning a home in Australia). It is clearly separable from guide_in/guide_uk by the country scope, though it never names those siblings explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It implies the use case — answering a home-related question for Australia — but offers no when-to-use/when-not guidance, no mention of alternatives like purchase_duty_au or house_prices_au, and no statement of what happens when no guide matches.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely useful behaviour beyond them: the response is a self-contained short answer plus a check date and page URL, the URL is intended for citation, and the same guide in other languages is returned when available. It stops short of stating what happens when no guide matches or whether the answer is authoritative, so a 5 is not warranted.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the country marker and the core purpose, and every clause carries information about scope, languages, or return shape. It is a single long run-on sentence, though, which slightly hurts scannability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description must describe returns — and it does, covering the answer, check date, URLs and cross-language variants. Parameters are fully covered by the schema. The remaining gap is the absence of fallback behaviour when no guide is found.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and both parameters are already documented with examples and enum semantics in the schema, so the description carries little extra burden. It adds only the implicit 'omitted = search all three' behaviour, which is already in the schema text, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb (finds the guide), the resource (Payotte guide), and the exact domain/scope (buying, financing, selling, renting or owning a home in Belgium), plus the three supported languages. That is enough to separate it from guide_au, guide_br, guide_es and the other country guides without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Topical scope is stated, so usage is implied: ask a Belgian home-related question and get a guide. But no when-not guidance or alternative routing is given, and the sibling set contains sharply overlapping Belgium-specific tools (purchase_costs_be, house_prices_be, borrowing_capacity_be, compare_regions_be) that a caller cannot distinguish this from. The description should say when to prefer this broad guide over those specialised tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only, idempotent, non-destructive, non-open-world behavior. The description adds value beyond those by specifying the return payload ('short answer, check date and URL') and the subject coverage, though it does not discuss rate limits or failure modes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with 'BRAZIL' and the core action, then a compact dash list of coverage topics. It is a single sentence and every element supports retrieval, though the topic list is long.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter guide lookup with no output schema, the description supplies the missing return fields and scope. It is sufficient to call correctly, with only minor absence of no-result behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the single 'query' parameter is already documented with examples. The description's topic list contextualizes query scope but does not add syntax or format rules beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Finds') and resource ('Payotte guide answering a question about a home in Brazil'), and the 'BRAZIL' prefix distinguishes it from sibling guide_* tools for other markets. The topic list further clarifies scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides only implicit guidance: use when you need a guide answer about a home in Brazil. It does not name alternatives (e.g., capital_gains_tax_br, purchase_costs_br) or state when not to use it, so the agent must infer the routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuine behavioral context beyond that: it returns a short answer plus a check date and URL, and that it is a lookup over curated guides rather than a live computation. It does not say what happens when no guide matches.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence with the country front-loaded, so the critical disambiguator is read first. It is dense but every clause (topics, return fields) carries information; no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter, read-only lookup with no output schema, the description covers purpose, scope, and return shape, which is enough for an agent to call it correctly. The missing piece is routing guidance against the many country- and topic-specific siblings.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Only one parameter and schema description coverage is 100% ('The question or keywords'), so the baseline is 3. The description's topic list marginally clarifies the intended query domain but adds no syntax, length, or formatting guidance beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Finds the Payotte guide'), the resource (Germany home guide), and the topical scope (buying, financing, selling, renting, owning). The 'GERMANY' prefix and the explicit country make it trivially distinguishable from the parallel guide_au/guide_be/guide_es siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The topical enumeration ('buying, financing, selling, renting or owning a home in Germany') implies when this guide is the right destination, but there is no explicit guidance on when to prefer it over narrower siblings like mortgage_payment_de, rents_de, or purchase_costs_de, nor any exclusion criteria. Usage is inferable but not stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint/idempotentHint/non-destructive, so the safety profile is covered. The description adds genuinely useful behavior beyond that: it returns a short answer, a check date, and a URL, which matters since there is no output schema. It doesn't cover failure behavior or coverage limits, keeping it below a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One front-loaded sentence with the country marker "SPAIN." first. Efficient, though the long parenthetical (NIE, IRNR, 3% withholding, golden visa) is keyword-stuffed rather than strictly necessary.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-parameter lookup with full schema coverage and annotations covering safety, the description supplies the missing return-shape info (short answer, check date, URL). An agent has enough to call it correctly; only routing guidance against overlapping siblings is absent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the single parameter is already documented as "The question or keywords." The description contextualizes the kind of question expected but adds no syntax, format, or length guidance beyond the schema. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ("Finds") and resource (the Payotte guide) and scopes it to SPAIN, listing the covered topics (buying, financing, selling, renting, owning). It distinguishes itself from the parallel country guides, though it doesn't explicitly say why an agent should pick this over the more specific siblings like non_resident_tax_es or purchase_costs_es.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the topic list (a question about buying/renting/owning a home in Spain), but there is no explicit when-to-use, when-not-to-use, or named alternative. It never tells the agent to prefer this broad guide versus the narrower Spanish tools that overlap in subject matter.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the safety profile is covered. The description adds real value beyond them by disclosing the return shape ("self-contained short answer, check date and URL") and the curated/dated nature of the content, which tells the agent how to present results and how to judge freshness.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One front-loaded sentence with the country and lookup intent first, then scope, then return value. Efficient, though the single sentence bundles purpose, scope and return contract into a fairly long clause chain.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly compensates by describing what comes back (short answer, check date, URL), and the sole parameter is fully specified. Annotations cover the safety profile; only sibling routing and any freshness/coverage limits are absent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Single parameter with 100% schema coverage, so the schema already documents that `query` is a question or keywords. The description adds only the topical scope of valid queries, which is marginally useful but no format or length guidance beyond the schema's own examples.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb+resource: "Finds the Payotte guide" scoped to India and to a clearly enumerated topic set (buying, financing, selling, renting, owning, NRI/OCI rules). The leading "INDIA." tag plus the Payotte framing separates it from the many country-specific siblings (guide_au, guide_uk, house_prices_in, home_loan_emi_in) without needing to open a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The topic list and "answering a question" framing imply when this tool is appropriate, but there is no explicit routing: an agent getting "what is stamp duty in India" cannot tell from this text whether to use this guide or stamp_duty_in / home_loan_emi_in / house_prices_in. No exclusions or alternatives are named.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so safety behavior is well covered. The description adds useful return behavior by stating it returns a short answer, check date, and URL, though it does not discuss auth, rate limits, or no-match behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the country scope with 'ITALY.' and packs purpose, topic coverage, and return payload into a single efficient sentence. Every phrase contributes and there is no repetition or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter guide lookup with no output schema, the description is mostly complete: it states the country, topical scope, and returned fields. It omits only edge-case behavior such as what happens if no guide matches, which is a minor gap for this complexity level.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with the single query parameter already described as 'The question or keywords.' The description adds topical scope for what the query should concern, but does not add query syntax, formatting guidance, or handling details beyond the schema. Baseline 3 is appropriate when the schema already documents the parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Finds), a clear resource (the Payotte guide), and a precise scope (ITALY, buying/financing/selling/renting/renovating/owning a home). The country scope clearly distinguishes it from sibling country guides such as guide_es or guide_de.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear context: use when seeking an Italian home guide answer about buying, financing, selling, renting, renovating or owning. It does not explicitly state when not to use it or name alternative sibling tools, but the Italy scope makes the correct routing obvious.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark this as a safe, read-only, idempotent, closed-world lookup, so the safety burden is covered. The description adds genuinely new behavior: it returns a "self-contained short answer, check date and URL," which is the key contract for an agent since there is no output schema. It stops short of describing truncation, matching confidence, or fallback when no guide matches.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence, front-loaded with the country marker and the core verb, and the parenthetical topic list earns its space by defining scope. It is dense but not padded; only minor readability cost from stacking several clauses.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter, annotation-covered lookup with no output schema, the description supplies purpose, topic scope, and return shape. The remaining gap is routing guidance against the many sibling guide/professional tools, which an agent would have to infer.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema already supplies example queries, so the baseline is 3. The description goes further by enumerating the queryable domains (restricted zone, fideicomiso, notary, deed, financing, resident/non-resident income tax on sale), which helps the agent judge whether its question is in scope and how to phrase it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Finds the Payotte guide answering a question about...") scoped to MEXICO, with the topical coverage (buying, financing, selling, renting/owning) spelled out. This differentiates it from cost/price/calculator siblings such as closing_costs_mx, home_prices_mx and mortgage_payment_mx, though it never explicitly routes against the other guide_xx tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: an agent can infer it should call this for a Mexico home-ownership question. There is no explicit when-to-use/when-not statement, no mention of the parallel guide_au/guide_br/guide_es tools, and no indication of what happens if the question falls outside the listed topics.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavior by naming the return payload (self-contained short answer, check date, URL) and confirming the closed Payotte-only corpus, which matters because there is no output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One dense sentence with the geographic scope front-loaded and zero filler; every clause (domain, retrieval action, return contents) carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description usefully enumerates the returned fields, and annotations cover safety, so an agent has what it needs to call this. It omits the no-match/empty-result behavior and gives no hint about result granularity, which keeps it short of a 5.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Only one parameter and schema description coverage is 100%, so the schema already explains that 'query' takes a question or keywords with examples. The description adds no syntax, format, or length guidance beyond that, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Finds the Payotte guide answering a question') plus the topical scope (buying, financing, selling, renting, owning a home in the UK). The 'UNITED KINGDOM.' prefix separates it from guide_au and guide_in, but it does not differentiate against topically overlapping UK siblings such as house_prices_uk or purchase_tax_uk.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied: reach for this when a user asks a UK home-buying/owning question that a short editorial answer would satisfy. There is no explicit when-not, no mention of alternatives (e.g. use purchase_tax_uk for tax figures), and no guidance on how to phrase the query.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare this a safe, idempotent, read-only, non-open-world calculation, so the safety profile is covered. The description adds genuinely useful context the annotations do not: the default interest rate source (RBI weighted average lending rate on fresh housing loans) and that it is the latest month and provisional. It still says nothing about how LTV caps vary by loan size or what the returned figures look like.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense sentence with the market ('INDIA.') front-loaded and the scope stated before the default-rate caveat. No wasted clauses, though the all-caps market tag and semicolon-chained outputs make it slightly terse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a three-parameter calculator with full schema coverage and annotations carrying the safety profile, the description covers the operation, its outputs, and the default-rate assumption. The absence of an output schema is mitigated because the description enumerates the three returned values; only edge-case behavior for LTV caps is unstated.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so loan_amount, tenure_years, and interest_rate are already documented, giving a baseline of 3. The description corroborates the optional interest_rate by explaining its fallback source, but adds no units, bounds, or formatting beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the resource (home loan EMI) and enumerates the outputs — EMI, total interest, and RBI loan-to-value caps — for the India market, which no sibling covers. It is a noun phrase rather than an explicit verb like 'calculate', but the intent is unambiguous and distinguishable from the price/tax/guide siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to use this tool versus alternatives such as taux_courants, acheter_ou_louer, or compare_states_in, nor any prerequisite guidance. The only conditional info is about the default rate, which is a parameter detail rather than usage routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare this a safe, read-only, idempotent operation, so the safety profile is covered. The description usefully adds data-scope constraints (Jan.-June 2026 vintage, pesos available by state only, index by state or municipality), which is genuine behavioral context. It does not describe return format or limits, so it adds moderate rather than rich value beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence leads with the country and source, then enumerates the returned metrics and the geographic granularity. No filler. It packs several facts into one sentence, which borders on dense but stays readable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-value burden and does so adequately by naming the metrics, units, and geographic breakdown. Annotations handle safety. The main omission is period/coverage caveats beyond the stated Jan.-June 2026 window, but for a single-parameter lookup tool this is fairly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the single 'place' parameter is fully documented in the schema (including empty = national). The description mentions state/municipality scope, but the subtle detail that peso prices exist by state only is not tied explicitly to the parameter, so it adds little beyond the schema. Baseline 3 for high coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific source (Sociedad Hipotecaria Federal) and states exactly which metrics are returned: median/mean appraisal value by state and the year-over-year price index change by state or municipality. It is clear what an agent gets back. It does not explicitly differentiate itself from siblings like house_prices_* or compare_states_mx, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the content (query Mexican SHF appraisal/index figures) but there is no explicit when-to-use, when-not-to-use, or named alternative among the many sibling price tools. An agent can infer the domain but must guess how this differs from compare_states_mx or the country price tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuine value by naming the data sources (Census ACS, FHFA House Price Index) and noting periods and sources are included, which tells the agent about data provenance and vintage. It stops short of covering update cadence, coverage limits, or failure modes, so a 3 is appropriate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense sentence with no filler, and the country scope is front-loaded so the agent filters it against siblings immediately. The parenthetical source attributions interrupt the flow slightly but each earns its place by indicating data provenance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter lookup with no output schema, the description adequately signals the return payload (median value, one-year change, periods, sources) so the agent knows what it gets back. The only real gap is the absence of routing guidance against closely related US tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the single 'state' parameter is already documented with accepted formats, so the baseline is 3. The description adds one implicit detail — that city is not a parameter but is derived as the state's main city — but nothing about the state value syntax beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: median home value for a US state and its main city, plus the one-year price change. The 'UNITED STATES' prefix clearly disambiguates it from house_prices_au/uk/in and the other country-specific siblings. It does not, however, explicitly contrast itself with near-neighbors like state_overview_us or compare_states_us.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no exclusions, and no named alternative. An agent cannot tell from the description whether to call this or state_overview_us / compare_states_us for a given user question.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, so safety is covered. The description earns its keep by adding what annotations cannot: data provenance (OMI, Agenzia delle Entrate, ISTAT), temporal coverage including provisional 2025, and hard coverage limits (only 20 regions, only the 20 top-selling cities). It still says nothing about response shape, but with no output schema that is the main omission.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence, front-loaded with the country marker 'ITALY.' and then the data definition. Every parenthetical (OMI register, provisional, ISTAT) carries provenance information that matters; there is no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-optional-param lookup with no output schema and read-only annotations, the description supplies scope, years, granularity and source, which is close to sufficient. It omits the return shape and what happens for an out-of-scope place, minor but noticeable gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema already defines 'place' with examples and the empty-string default, so the baseline is 3. The description adds genuine value beyond the schema by revealing that only 20 regions and the 20 highest-selling cities are served, which constrains what a valid 'place' value can be and warns against assuming arbitrary municipalities.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource (home sales data for Italy) and pins down the exact scope: 2024/2025, 20 regions and top-20 cities. An agent knows immediately this is Italian residential transaction data, not prices or mortgage data. It never explicitly names a sibling (e.g. compare_regions_it, stats_marche) to disambiguate, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The text describes content only; it gives no when-to-use condition, no prerequisite, and no alternative tool to prefer for regional comparison or price queries. With siblings like home_prices_us, house_prices_es and compare_regions_it in the same family, the absence of routing guidance is a real gap.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower, yet the description adds real domain context: it discloses the ABS source, that only the latest quarter is returned, and that mean and median values are not comparable. That comparability caveat is valuable information not present in structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, front-loaded with the country and dataset. The only slightly cryptic line is 'The price_type field says which', which references a return field absent from the schema, but it still earns its place by disambiguating the two measures.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-optional-parameter, read-only lookup with no output schema, the description supplies nearly everything an agent needs: source, recency, area semantics, and the mean/median distinction. Minor omissions (currency/units explicitly stated, historical breadth) are low-impact.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, but the description goes further by explaining that the meaning of the result changes with the area type (state/territory yields MEAN, capital city or 'rest of state' yields MEDIAN). That semantics-of-input mapping is genuinely useful beyond the schema's bare examples.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource (ABS Total Value of Dwellings, latest quarter) tied to a specific country, and immediately differentiates itself from the house_prices_in / house_prices_uk / home_prices_us siblings via the AUSTRALIA scoping. An agent can identify exactly what dataset this returns.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'AUSTRALIA.' prefix implicitly routes the agent to the correct country tool, but no alternative is named and no when-not condition is given. Usage is implied by geography rather than stated explicitly.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the bar is low; the description adds valuable domain constraints beyond them: exactly 55 covered areas, the source registry (Statbel/FPS Finance), and the suppression rule 'no median under 16 sales'. It also enumerates the returned metrics (median, sales count, 1y/10y change, latest quarters). It does not state fallback behavior when an area is uncovered.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One dense but well-ordered sentence-sequence: country front-loaded, then metrics returned, then valid area granularity, then supplier and suppression caveat. No filler. Slightly packed for a single paragraph, but every clause carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter, non-destructive read with no output schema, the description covers the essentials: what is returned, at what geographic granularity, from what source, and the reliability caveat. An agent has everything needed to call it correctly and interpret the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the single 'area' parameter already carries concrete examples with the useful Brussels/Bruxelles disambiguation. The description adds only the '55 covered' constraint, which is a coverage note rather than parameter syntax. Baseline 3 is appropriate when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource (median price of houses and apartments) with explicit geographic scope (Belgium) and data provenance (Statbel medians of recorded resale deeds). The 'BE' qualifier combined with '55 covered' municipalities instantly separates it from house_prices_au/es/in/uk and home_prices_us/mx without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the required area parameter and the enumeration of valid area granularities (municipality, province, Region), but there is no explicit when-to-use guidance and no routing to alternatives such as stats_marche, compare_regions_be, or acheter_ou_louer. The agent must infer that this is the price-lookup tool rather than the market-overview tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare this a safe, idempotent, closed-world read, so the safety burden is offloaded. The description adds useful provenance the annotations cannot convey — data source (Ministry, INE), vintage (Q2 2026), and coverage breadth — but says nothing about caching, rate limits, or how missing places are handled.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One dense sentence, front-loaded with the country identifier and packed with scope, source, period, and metrics. Nothing is wasted or repeated.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a low-complexity single-parameter lookup with rich annotations and no output schema, the description does state which values come back (per m² value, one-year change, regional index). It stops short of describing the return structure, but given the tool's simplicity and the annotation coverage this is nearly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the single 'place' parameter already carries examples and the empty-string default in the schema. The description adds no extra syntax or semantics beyond what the schema supplies, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a concrete resource (Ministry average appraised value per m²) plus the exact coverage (55 cities, 19 regions), the change metric, and the INE index, so the agent knows precisely what data this returns. The leading 'SPAIN.' and the _es suffix separate it from the other country-level house_prices_* tools, but it never distinguishes itself from the potentially overlapping compare_regions_es sibling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to pick this tool versus house_prices_uk/au/in, home_prices_us/mx, compare_regions_es, or stats_marche. The agent must infer usage purely from the country marker in the description and tool name, which is minimal guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds real value beyond them by disclosing the data limitation: values are index/yoy changes, not rupee prices, and no open series provides city-level rupee prices.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences, front-loaded with the 'INDIA.' scope marker followed by the sources and the key limitation. Every clause carries information; nothing is redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-optional-parameter, annotation-covered read tool, this is nearly complete: it identifies the sources, coverage, and that output is yoy index change. With no output schema, a bit more on result shape or units would fully close the gap, but the essential call information is present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the single 'city' parameter is fully documented with an example and the empty-value behavior. The description adds no parameter detail beyond the schema, so the baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the exact resources (RBI All-India House Price Index over 18 cities and NHB RESIDEX year-on-year change) and the country scope, so it is immediately distinguishable from the sibling house_prices_us/uk/au tools. An agent knows precisely what data this returns without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the country/data scope, and the sentence 'Indices only: no official open series gives rupee prices by city' usefully sets a when-not expectation about rupee prices. However, it never names an alternative or states the condition under which another tool (e.g. compare_states_in, stats_marche) should be chosen instead.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare this a safe, read-only, idempotent, non-open-world operation, so the safety profile is fully covered and the description is not required to restate it. The description adds the useful temporal constraint ('latest month'), but says nothing about data recency, revision behavior, or how areas are matched, which the annotations do not supply.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence that front-loads the scope marker 'UNITED KINGDOM' and then enumerates the returned metrics and geography levels. Dense but every clause carries information; the long list of metrics is the only mild bloat.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly enumerates what the tool returns (average price, 12-month change, price by property type, first-time buyer price) and the geography granularity, which is the information an agent needs to decide if this answers the query. Only minor gaps remain, such as data vintage beyond 'latest month'.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema already documents examples and the empty=UK default, so the baseline is 3. The description goes slightly beyond it by defining the valid area universe (a nation, an English region, or one of the 20 areas Payotte covers), which directly informs what strings the 'area' parameter will accept.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific resource and scope: UK average home price plus 12-month change, property-type breakdown and first-time buyer price, for the UK, a nation, region or one of 20 covered areas. It also implicitly distinguishes itself from the many sibling price tools (house_prices_us/au/in) via the UK/US/UK-region scope, though it never names them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: an agent can infer this is the tool for UK house price figures, but there is no explicit when-to-use, when-not-to-use, or pointer to alternatives such as compare_nations_uk or stats_marche. No caveats about which geography the user must supply are given beyond the schema.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, and the description still adds real substance: how each system behaves (constant vs falling payment) and the provenance of the default rate (Banco Central average on new housing loans to individuals, latest month). It does not clarify error behavior or whether the output includes a full amortization schedule.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense sentence with the country scope front-loaded and zero filler. The semicolon-chained clauses about the default rate are packed tightly but each carries information, so little is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description must describe returns, and it does list the payment under both systems, total interest, and LTV caps. For a three-parameter, one-required calculator this is nearly sufficient; the main missing piece is routing guidance against the many sibling jurisdiction calculators.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds meaning beyond the schema by explaining what happens when interest_rate is omitted — a Banco Central average rather than a fixed literal. It also frames the loan_amount as reais and the term as years, reinforcing the schema's own notes.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the resource precisely (Brazilian mortgage monthly payment) and specifies the two amortization regimes (Price and SAC) plus the companion outputs (total interest, CMN LTV caps). The 'BRAZIL' prefix and the Portuguese-system-specific terms clearly separate it from mortgage_payment_es and mortgage_payment_mx, though no sibling is named and there is no explicit verb ('computes').

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Nothing states when to reach for this tool versus taux_courants, purchase_costs_br, or the other national mortgage calculators. Usage is only implied by the tool's nature as a payment calculator, which is the definition of implied guidance rather than explicit when/when-not routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare this as a safe, idempotent, non-destructive read (readOnlyHint, idempotentHint), so the safety burden is covered. The description goes beyond them by disclosing the fallback behavior: when no rate is given it uses the Bundesbank average effective rate on new housing loans fixed 5-10 years for the latest month, and it also returns the other fixation periods. No permissions or limits are mentioned, but for a read-only calculator this is solid added context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences, front-loaded with jurisdiction and the computed outputs, with the default-rate behavior following. The 'GERMANY.' fragment is terse but functional as a routing tag; almost nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description carries the return-value burden, and it does so at a reasonable level: it states the two headline outputs and mentions the additional fixation periods. For a deterministic read-only calculator with full schema coverage, this is close to complete, though it could say more about the shape of the returned fixation-period data.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the parametric baseline is 3. The description adds meaning beyond the schema by explaining what happens when interest_rate is omitted (the Bundesbank default) — a behavior the schema only labels 'optional' — and by indicating that fixation periods beyond the 5-10 year default are also returned.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the specific outputs (monthly payment and total interest of an annuity loan) and pins the jurisdiction with the leading 'GERMANY.' tag, which cleanly separates it from the many sibling mortgage_payment_* tools. An agent can tell what it computes and for which country without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the country tag and the annuity-loan framing, so an agent can infer this is the German tool for loan-payment math. However, there is no explicit when-to-use statement, no note on when a sibling such as purchase_costs_de or taux_courants is the better choice, and no stated prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive behavior, and the description adds meaningful context beyond them: the default interest rate falls back to Banco de España's three-year average (latest month), and the tool also returns the 12-month Euribor. It does not describe output formatting, but it does disclose what is computed, which is the key behavioral fact for a calculator.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense sentence with the market scope front-loaded and no filler. It is efficient, though the semicolon-joined clause about the default rate and the Euribor return is slightly crammed for easy parsing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only calculator with no output schema, the description covers what is computed, the default-rate behavior, and the secondary return value. The one gap is that it never states the required loan_amount input or the term default of 25 years in prose, but the schema carries those details.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all three parameters, setting a baseline of 3. The description adds value by pinning down the default for the optional interest_rate — the Banco de España three-year average rather than the bare 'optional' the schema gives — which is exactly the ambiguity an agent would otherwise face.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific computation (monthly payment and total interest of a repayment mortgage) for a specific market (SPAIN), plus a secondary return (12-month Euribor). The 'SPAIN' prefix cleanly distinguishes it from the sibling mortgage_payment_br, mortgage_payment_mx, and home_loan_emi_in without needing to open any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the name and market scope — an agent can infer this is the Spanish mortgage calculator. However, there is no explicit when-to-use/when-not guidance and no reference to the sibling alternatives, so it stays at the implied level.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive, so the safety bar is low. The description adds real value beyond them: the ECB data source, the default fixation period (fixed 5 up to 10 years, latest month), and the fact that other fixation periods are also returned. It stops short of describing rounding, currency handling, or amortization detail.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the country scope and the core computation; two clauses of dense, relevant content. The trailing 'Also returns the other fixation periods' is slightly cryptic and would read better tied to the output, but nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-value burden and mostly does so (monthly payment, total interest, other fixation periods). The default-rate explanation closes the main parameter ambiguity. Minor gaps remain around output units/format and precision, but the essentials are present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds genuine semantics for interest_rate by explaining the default ECB rate and its fixation period when the parameter is omitted. The term_years and loan_amount semantics are left to the schema, which already documents them.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific computation (monthly payment and total interest of a constant-instalment loan) and scopes it to Italy via the leading 'ITALY.' marker, which cleanly distinguishes it from the country-specific siblings mortgage_payment_de/es/br/mx. An agent can tell what it does and which country it targets without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied (compute an Italian mortgage payment) with no explicit when-to-use, when-not-to-use, or named alternatives among the mortgage_payment_* siblings. It does explain the default-rate context, but that is behavioral detail rather than routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description earns credit by disclosing the fallback behavior when interest_rate is omitted — the default is the Banco de México average of advertised fixed-rate offers for the latest month — and by naming the additional reported figures (average CAT, Banxico target rate). It stops short of describing calculation assumptions or rounding.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense sentence with the country marker and primary outputs front-loaded, and no filler. It is packed but every clause (default rate source, extra outputs) carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description must carry the return values, and it does name monthly payment, total interest, average CAT, and the Banxico target rate. Combined with full parameter coverage, this is nearly complete; only calculation conventions remain unstated.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning beyond the schema: it explains what the optional interest_rate parameter defaults to and what source that default comes from, which the schema's '% a year (optional)' does not convey.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific output (monthly payment and total interest) for a specific resource (fixed-rate peso mortgage) and pins the scope with 'MEXICO.' and 'peso'. This clearly separates it from mortgage_payment_br and mortgage_payment_es without the agent opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the country and currency markers, so an agent can infer this is the Mexican mortgage calculator, but there is no explicit when-to-use statement, no exclusion, and no pointer to alternative siblings. Adequate but with a clear gap.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint and non-destructive, so the safety profile is fully covered. The description adds the useful scope constraint of 14 high-risk states and lists the content categories returned, but does not say which 14 states, nor how a non-covered state behaves.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short, front-loaded sentences with the geography stated first and coverage limits placed last. Minor redundancy between the 'UNITED STATES' prefix and the '_us' name, but no wasted prose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With one required parameter, no output schema and annotations covering the read-only profile, the description is close to sufficient: it names the data categories returned and flags the limited state coverage. The main remaining gap is not enumerating the 14 covered states.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the single 'state' parameter already documents accepted formats (name or two-letter code). The description adds nothing about the parameter, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a concrete subject and sub-parts: the main natural hazards for a home in a US state, the insurer of last resort, and hazard disclosure rules. It gives an agent enough to know the payload, though it never differentiates itself from near-neighbours such as seller_disclosure_us or state_overview_us.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use or when-not-to-use statement and no sibling is named as an alternative. The only routing signal is the coverage note 'Covered: 14 high-risk states', which implicitly warns the agent this tool is not universal for all 50 states.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is low. The description nevertheless adds real domain behavior: the 2% / 1.1% basis on cadastral value and the 24% / 19% applied rate, plus the tax year, which an agent can use to sanity-check or explain the result.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense sentence with the country and the tax name front-loaded, and no filler. The nested parentheticals carry rate detail that is genuinely useful, though the stacking makes it slightly heavy to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.