chathome.lu — Luxembourg Real Estate

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

Annotations already indicate non-read-only behavior. The description adds that it persists the full user-scoped analysis and returns a summary, which gives useful behavioral context beyond the annotations. It also includes a safety warning about not sending sensitive data, which is relevant for a tool that processes user-provided content. No contradiction with annotations exists.

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 description is only two sentences, front-loaded with the core purpose and then a warning. It is succinct, with no redundant information, and each sentence adds 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?

The tool has moderate complexity (4 params, non-read-only, output schema). The description covers the main function, side effect (persist), and output. It mentions the Luxembourg context. It does not explain what constitutes a risk summary or edge cases, but given the output schema exists, this is adequate.

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?

The schema already provides descriptions for text and pdfBase64 (including sensitive data warnings). The description mentions 'lease PDF or raw text' linking to these params but does not clarify filename or language semantics. With 50% schema coverage, the description adds marginal value but does not fully compensate for undocumented parameters.

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 clearly states the tool's function: analyzing a Luxembourg residential lease from a PDF or raw text, persisting the analysis, and returning a compact risk summary. It distinguishes itself from sibling tools (which are mostly read/search operations) by being the only lease-analysis tool.

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: when a caller provides a lease document to analyze. It does not explicitly mention alternatives or when not to use, but the context is clear from the purpose. It would benefit from explicit 'use when...' guidance, but the intent is understandable.

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 the description adds real substance on top: results split known from unknown components and knownTotal deliberately excludes unknowns, a decision that prevents misreading the output. It stops short of explaining how enum value 'unknown' propagates through the calculation or what errors look like beyond refusal.

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?

Dense but front-loaded: the scope, the conditional components, and the output contract (knownTotal excludes unknowns) arrive before the refusal rule. The single long sentence cramming eligibility, surcharge, and notary logic is slightly harder to parse than a short list would be.

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 9 parameters, nested quotes, an output schema, and full annotation coverage, the description supplies exactly the missing layer: which components are conditional, what happens to unknowns, and what input domain is rejected. An agent can call this correctly and interpret the result without further documentation.

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?

At 56% schema coverage the description must compensate, and it does for the highest-risk fields: it ties eligibility/balance inputs to 'only when confirmed', maps the municipal surcharge to a confirmation requirement, and explains that notary figures are either tariff-estimated or supplied as quotes. financing and the exact purchaseKind semantics remain undocumented in both places.

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 computation (Luxembourg resale purchase costs) and the exact inputs that drive it (price and main-home use), then enumerates the cost components it produces. It also carves out an explicit exclusion (new-build/VEFA is refused), which separates it from the mortgage, affordability, and buy-vs-rent 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 a clear when-not (VEFA purchases are refused) and conditional guidance for the Bëllegen Akt credit and Luxembourg City surcharge ('only when confirmed'). It does not name a sibling to use instead for new-build or for pure financing math (calculate_mortgage), so an agent must infer the handoff.

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?

Beyond the read-only/idempotent annotations, it discloses important behavioral caveats: the winner stays null until all acquisition costs are confirmed, knownCostWinner is conditional on currently known costs, and the result is a scenario rather than a verdict. It also notes that the tool returns a prefilled website link, which is useful context not covered by 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?

The description is dense and front-loaded with the core purpose before caveats and output behavior. The sentence about winner and knownCostWinner is somewhat jargon-heavy, but every part carries useful 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 complex 8-parameter simulation tool with an output schema, the description supplies the essential framing, caveats, and result-link behavior. Remaining gaps are minor, such as not clarifying the commune parameter's role or when to prefer this over adjacent 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?

With only 50% schema description coverage, the description meaningfully compensates by naming most inputs and clarifying that rent must be comparable and mortgage rate is an explicit assumption. It covers down payment, loan term, horizon, and property tax, though it does not explain the commune parameter or add units where the schema lacks descriptions.

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 comparison (buying vs renting the same Luxembourg home over time) and the key inputs that drive it. It is clearly distinguishable from siblings like calculate_mortgage or analyze_lease, which cover narrower pieces rather than the full buy-vs-rent comparison.

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 explains that the tool works from explicit assumptions and uses the website simulator, which tells the agent when this tool is appropriate. It does not explicitly name alternatives or state when not to use it, so it falls short of full 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?

The annotations already declare this is read-only, idempotent, non-destructive, and open-world, so the description need not repeat the safety profile. It adds useful scope limits: the rate is an assumption, returned costs are excluded from an all-in budget, schedule output is opt-in, and no account or loan application is involved. The phrase 'Returns excluded costs' is slightly ambiguous but still signals a bounded calculation.

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 core purpose is front-loaded in the first sentence, and the remaining sentences add useful scope caveats without rambling. It is compact for a tool with multiple behavioral limits, though the caveat sentences are dense and slightly overlap with annotation-provided 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?

Given the output schema, rich annotations, and mostly described input schema, the description supplies the remaining non-obvious context: rate assumptions, excluded costs, opt-in schedule generation, and no account or application requirements. An agent has enough information to invoke it correctly without needing a broader housing-budget interpretation.

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 80%, so most parameters are already documented well in the input schema. The description reinforces the meaning of annualRatePct as an explicit assumption and includeSchedule as opt-in, and it refers generally to extra-payment scenarios. However, it adds little parameter-level detail beyond the schema, so 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 states a specific verb and resource: calculate monthly loan payments, total interest, and extra-payment scenarios from explicit principal, annualRatePct, and years. It also distinguishes the tool's assumption-based calculation from a bank quote, which helps separate it from rate-fetching or affordability 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?

It gives clear usage context by saying the rate is a stated assumption rather than a bank offer and that the result is not an all-in housing budget. It also says to request includeSchedule only for a detailed repayment table. It does not explicitly name sibling alternatives such as get_mortgage_rates or get_affordability, so it falls short of full 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 readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely useful context the annotations cannot: the computation basis (5% of revalued capital), the confidence-tier behavior ('only verified is the legal figure'), and a 'Not legal advice' disclaimer. However, it doesn't say what happens when both input modes are supplied, or how confidence tiers other than 'verified' should be treated.

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 sentences with the legal basis front-loaded, then input modes, then the confidence caveat, then the disclaimer. Dense and telegraphic phrasing ('and/or price, purchaseYear and buildingYear (optional land price and works)') costs a little readability but no sentence is 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 an output schema present, return values needn't be explained, and a read-only seven-parameter calculator is adequately covered by the stated input modes and confidence semantics. The remaining hole is the works/worksYear pairing and whether the two calculation modes can be combined in one call.

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 43%, so the description has to compensate, and it largely does: it names monthlyRent, price, purchaseYear, buildingYear, and implicitly landPrice and works, and it explains what each mode computes rather than just naming the field. Gaps remain for worksYear and worksAmount (grouped vaguely as 'works'), and it never states that all inputs are optional or how partial inputs are handled.

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 domain-specific resource: computes the Luxembourg legal rent ceiling as 5% of revalued invested capital, and does so in both directions (rent→implied capital, price/years→owner ceiling). This is clearly distinguishable in substance from siblings, though it never names an adjacent tool like calculate_rent_subsidy or analyze_lease to draw the boundary 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?

Gives concrete call guidance: 'Give monthlyRent to see the capital a rent implies, and/or price, purchaseYear and buildingYear ... for the owner's ceiling.' That tells the agent which input mode produces which answer, plus the interpretive rule that only confidence 'verified' is legally meaningful. It stops short of stating when to prefer a sibling tool or when this tool is not applicable.

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), and the description adds genuinely new behavioral context: the result is indicative only, thresholds are dated, checkpoints are returned step-by-step, and the outcome is not an entitlement. It stays consistent with openWorldHint since official thresholds are external. It stops short of describing precision or jurisdiction limits, so a 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?

Two tightly packed sentences with no filler: the first states what is computed and from what, the second carries the legal qualification. The purpose is front-loaded and the caveat is placed where it will still be read.

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?

An output schema exists, so return values need not be explained, and annotations cover safety; the description therefore only needed to supply the computational input list and the caveat about non-entitlement, which it does. Minor gaps remain around jurisdiction/residency eligibility and currency, but nothing essential to calling it correctly 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 coverage is only 50% — householdSize and dependentChildren have no schema descriptions — but the description explicitly names both, plus 'previous-year monthly net income', so the undocumented parameters are disambiguated. It does not specify units or accepted ranges, which the schema covers for the other two fields, so it does not exceed a 4.

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 gives a specific verb and resource — calculating the Luxembourg rent subsidy (subvention de loyer) — and enumerates the four determinants, so an agent knows exactly what computation is being performed. It does not explicitly name how it differs from near-neighbours such as calculate_rent_ceiling or get_affordability, which keeps it below 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?

Relevant usage is only implied: the listed inputs (household size, income, rent) signal the scenario, but there is no explicit when-to-use, when-not-to-use, or pointer to an alternative sibling. The closing 'Ministry decides' sentence is a legal caveat 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 declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds genuinely new behavioral context: nothing is stored, each fact carries status/source/date, and coordinate queries are scope-limited. Return shape is signalled without duplicating the 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?

Two sentences, front-loaded with what the tool returns, then the mode caveat. Dense with semicolons but nearly every clause carries new information; the 'information, not legal advice' and 'nothing is stored' clauses are short, purposeful disclaimers.

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?

An output schema exists so return values need not be re-explained, and the description still previews the result fields usefully. For a four-parameter, zero-required tool the main gap is the undocumented communeName and the lack of any statement about what happens when neither identifier is supplied.

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 25%, with just parcelRef documented, so the description must compensate. It does explain the lat/lng vs parcelRef semantic difference well, but communeName is left entirely unexplained in both schema and description.

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 ('Luxembourg plot check') from either a parcelRef or lat/lng, and enumerates exactly what comes back: PAG zoning, buildable envelope, buildings/planning, flood and heritage constraints. This is clearly distinguishable from the pricing, mortgage and listing 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 explicit mode-selection guidance: coordinates yield location-scope context only, while parcel identity and buildable figures require the cadastral reference. It also sets the expectation that output is informational, not legal advice. It does not, however, point to any sibling tool 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 declare readOnlyHint, idempotentHint, openWorldHint, and non-destructive behavior, so the safety profile is covered. The description adds important behavioral context beyond annotations: no account linking is required, results are limited to active publicly eligible listings, and missing values must not be treated as equality or zero. These caveats materially affect how an agent should interpret results.

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 purpose is front-loaded in a single sentence, and every clause conveys scope or a data caveat rather than filler. It is dense because it enumerates many compared fact categories, but the density is justified and there is no redundant 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?

An output schema exists, so return structure need not be explained in the description. The description covers the comparison scope, accepted inputs, eligibility filtering, normalized fact categories, and the critical missing-value caveat, leaving little an agent needs to infer before calling 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%, and the schema already documents the ids array's min/max items and the locale enum. The description repeats the two-to-eight range and confirms ChatHome URLs are accepted, but adds no further parameter syntax, format, or validation detail beyond what the schema provides.

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 uses the specific verb 'Compare' with the resource 'listings', states the accepted input range (two to eight listing IDs or ChatHome URLs), and makes clear this is a multi-listing comparison rather than a single-listing lookup. An agent can distinguish it from siblings like get_listing or search_rentals without inspecting 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?

It establishes the comparison context and input constraints, but never explicitly says when to use this tool instead of get_listing, get_listing_truth, or search tools, nor does it state when not to use it. Usage is implied by 'Compare two to eight' rather than routed against alternatives.

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 open-world, so the safety profile is covered. The description adds one genuinely useful behavioral note — that the output discloses whether the property-price ceiling covers all acquisition costs or only known costs — but says nothing about the Bëllegen Akt handling, deprecated parameters, or how unconfirmed inputs degrade the result, all of which matter for a compliance-sensitive calculation.

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 sentence, front-loaded with the purpose, so it is not verbose. However, the second clause about the property-price ceiling is awkwardly worded and reads as an implementation caveat rather than actionable guidance, and it consumes half the description's limited budget.

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?

An output schema exists, so return values need not be explained, but with 16 parameters, 6 required, 4 enums, and deprecated compatibility fields, the description leaves the agent without critical context: which inputs are decisive, how omissions change the answer's confidence, and how this differs from the other mortgage tools. It is under-specified for a tool of this complexity.

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 56%, and the description contributes nothing about any of the 16 parameters, including the risk-sensitive ones (bellegenAktEligibleBuyers, bellegenAktCreditAvailable, residenceUse) or the two explicitly deprecated flags. An agent must read the whole schema to learn that isFirstTimeBuyer and isPersonalResidence are deprecated, and nothing in the description warns that omitting residenceUse yields an 'unconfirmed' position.

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 domain: 'Calculate Luxembourg mortgage affordability', which is distinguishable from siblings like calculate_mortgage and get_quick_estimate by its jurisdiction and affordability focus. It does not name a sibling to differentiate itself, but the resource is concrete enough for an agent to recognize.

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?

No indication of when to use this versus calculate_mortgage, get_quick_estimate, or get_mortgage_rates, all of which sound closely related. There is no mention of prerequisites, when results are authoritative, or when a lighter estimate tool would suffice.

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 open-world, so the safety bar is covered. The description adds real behavioral context beyond that: the country default, what the result carries (calculation dates, scenario, fare, location scope), and a no-fabrication guarantee that unavailable routes are not substituted with nearby towns.

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?

Dense and front-loaded, with the scope sentence first and the default and guarantees after. The clause 'Read calculation dates, scenario, fare and location scope' is slightly awkward and partly redundant with the output schema, costing a point.

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 annotations covering safety and an output schema covering returns, the description supplies the domain framing, default value, and failure semantics an agent needs. Only edge behavior for unsupported communes is left 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 0%, so the description must carry the load, and it does: it explains that commune is a municipality centre in a supported country, that country defaults to LU, that destination is one of six Luxembourg employment hubs, and that mode spans four options. It stops short of clarifying the expected commune naming format or what each destination slug denotes.

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 (municipality-centre commute scenarios) with concrete scope: origins in LU/FR/BE/DE, six Luxembourg employment hubs, four modes. No sibling tool covers commute computation, and the description makes that unique role unmistakable.

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 scenario framing and the 'Country defaults to LU' default, but there is no explicit when-to-use/when-not guidance or named alternative. For a tool with no close sibling this is tolerable, but the agent must infer the trigger condition.

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, and destructiveHint=false, so the safety profile is covered. The description adds that the full thread is returned on each call, which is modestly useful for idempotent polling, but no poll cadence, timeout, or termination condition is given.

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 the action and followed by the return value. No filler or redundancy.

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?

An output schema exists, so return details need not be repeated, and the tool is a simple one-parameter read. The only missing element is polling guidance, which is minor for a read-only status check.

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 with 100% schema coverage; the schema documents conversationId including its provenance from submit_inquiry. The description contributes no additional parameter meaning, 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 verb+resource ('Poll an MCP agent inquiry conversation') and the return ('current status and full message thread'), so an agent immediately knows this is the read-side counterpart to submit_inquiry. It never names a sibling to differentiate against, which keeps it at 4 rather than 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?

'Poll ... for agent replies' implies usage after an inquiry is created, but the description never states when to call it, how often to poll, or what to do instead if no reply exists. Usage is inferred from context, not spelled out.

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 behavior, and the description adds substantial context beyond them: no account linking, fail-closed output, source text treated as data rather than instructions, and explicit caveats that missing costs or imprecise coordinates never become confirmed totals or property-level checks. This is exactly the behavioral detail an agent needs for safe invocation.

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 description is front-loaded with the core action and remains information-dense rather than rambling. The long enumeration of returned sections is somewhat verbose, especially since an output schema exists, but it still communicates capability breadth and does not bury the primary usage.

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?

Given full schema coverage, an output schema, and rich annotations, the description is complete enough for correct invocation. It adds important caveats about fail-closed behavior, source text safety, and handling of missing or imprecise data that structured fields do not carry.

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 id/URL, locale, and includePhotos are already well documented. The description reinforces the ID-or-URL input mode but adds no extra semantics for locale, includePhotos, or URL handling 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 and resource: retrieve/review a listing by ID or ChatHome URL without account linking. It also enumerates the returned page contents, making the tool's purpose clear. However, it does not explicitly distinguish itself from siblings such as get_listing_truth or compare_listings, leaving the agent to infer routing.

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 context ('without account linking') but no explicit when-to-use, when-not-to-use, or alternative-tool guidance. It never mentions get_listing_truth, compare_listings, or any other sibling, so selection between listing-related tools is left unaddressed.

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 that this is a read-only, idempotent, non-destructive open-world lookup. The description adds valuable behavioral context beyond that: it discloses the privacy guarantee that no reporter identities are exposed and clarifies the breadth of returned trust information.

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 description is front-loaded with the core purpose and then lists the key data categories efficiently. It is dense but not bloated; the separate privacy sentence earns its place and is short.

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?

Given that an output schema exists, the description need not explain return values in detail. For a read-only lookup with full schema coverage and clear annotations, the description provides enough context about data scope and privacy, though it could improve routing guidance against sibling listing 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 coverage is 100%, so the input schema fully documents the listing ID and locale parameters, including the enum and deprecated alias. The description does not add parameter-level meaning beyond the schema, which is acceptable at the baseline for fully documented schemas.

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 identifies a specific resource and scope: a trust-layer view of a full listing page, with enumerated contents like public record, normalized costs, official checks, sources, freshness, unknowns, and correction totals. It implies differentiation from a basic listing lookup through 'trust-layer' and 'full fail-closed listing page,' though it never explicitly names a 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 explicit guidance on when to use this tool versus alternatives such as get_listing or get_market_context. The context of a 'trust-layer view' implies a use case, but the description does not state when-not-to-use or route the agent to a sibling.

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 read-only, idempotent, open-world, non-destructive, so the bar is lower. The description still adds real behavior: results are bounded, carry source dates, and can surface explicit unknown states, which tells the agent to expect gaps rather than infer missing 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 qualifiers packed efficiently; nothing is repeated from the title and no sentence 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 an output schema present and full parameter documentation, the definition only needs to frame the data's nature, which it does. The remaining gap is sibling routing for a family of property/commune 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 coverage is 100%, so both parameters (commune, locale) and the quarter-vs-commune caveat are already documented in the schema. The description adds no parameter-level meaning beyond the structured fields, which is the baseline 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?

States a specific verb ('Get') and resource ('property context for a commune'), and qualifies it as bounded, source-backed, and unknown-state-aware. The exact data domain (prices, yields, market stats) is left implicit, so an agent knows the shape but not the content of what comes back.

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 call this versus siblings such as get_price_estimate, get_town_agencies, or resolve_location, which all touch commune/property context. The only scoping cue ('bounded') is not an explicit when/when-not 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?

Beyond the annotations, the description discloses important data-quality behavior: stale, undated, or official initial-fixation bands are excluded from current full-term quotes. It also clarifies that these are market observations rather than personal offers and states what is returned regarding availability and observation date.

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 description is front-loaded with the core purpose and then adds only high-value caveats, return context, and a fallback instruction. Every sentence contributes useful guidance without 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?

Given zero parameters, rich annotations, and an output schema, the description supplies the necessary context: what the rates represent, what is excluded, what is returned, and how to proceed if unavailable. Nothing essential for correct invocation appears to be 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?

This tool has zero parameters, so the baseline score is 4. There is no parameter meaning for the description to add 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 verb and resource: getting current source-dated full-term fixed mortgage market observations. It also distinguishes the data from personal bank offers and from the downstream calculate_mortgage action, so an agent can understand its role 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?

It provides a clear fallback path: if rates are unavailable, ask for an explicit rate assumption before calling calculate_mortgage. This explicitly names the relevant sibling tool and the condition for using it. It does not spell out every possible alternative, but the primary workflow is clear.

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 open-world, so the safety profile is covered. The description adds genuinely useful context beyond that: the training data is asking prices, not deeds, which materially affects how the estimate should be trusted, and it names the returned components.

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 purpose and followed by the model-basis caveat and the return contents. 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 32-parameter valuation tool the description says nothing about which optional attributes actually matter, how missing fields are handled, or how confidence intervals narrow. The output schema covers return values, but the input side is the dominant gap given near-zero schema coverage.

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 32 parameters and only 6% schema description coverage, the description must compensate and does not – it mentions no parameters at all. The two described schema fields (locale, areaSqm) and the obvious enums carry some weight, but 28 optional inputs (energyClass, glazing, buildingCondition, renovationYear, etc.) have no explanation anywhere.

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 ('price estimate for a Luxembourg property') plus the model's basis, which is more than a restatement of the name. It does not differentiate from the sibling get_quick_estimate, so an agent cannot tell from this text alone which estimator to pick.

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 note that the model is trained on historical listing asking prices rather than deed-level sales implies the appropriate use case and a caveat on interpreting output. However, there is no explicit when-to-use, when-not-to-use, or guidance versus the sibling get_quick_estimate.

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 readOnly/idempotent/openWorld/non-destructive, and the description adds genuinely new behavioral context: no authentication required, no AI narrative, unknown facts stay unknown rather than being defaulted, and the response can include coverage and commune-average limitations. It doesn't mention rate limits or estimate reliability beyond the caveat list.

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: what it returns, the input policy, and the sibling alternative. No filler, and the most decision-relevant information (no account, numeric only) is front-loaded.

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?

Output schema and annotations are present, so return values and safety are covered elsewhere. But for a 32-parameter tool with almost no schema descriptions, the description leaves an agent under-equipped to supply the optional facts that drive estimate quality; the 'omitted facts stay unknown' policy is the only guidance.

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 only 6% across 32 parameters, so the description must carry the semantic load but provides only the general rule that omitted facts 'stay unknown.' It says nothing about which facts most affect the estimate, how commune/district/areaSqm interact, or the land vs. living-area distinction for areaSqm.

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 ('Get a numeric Luxembourg property estimate') and immediately scopes it: no account, no AI-written report. It explicitly contrasts with the sibling get_price_estimate, so an agent can choose 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 clear routing rule: use this for anonymous numeric estimates, use authenticated get_price_estimate for a full report. It also states the input policy ('supply explicit property facts; omitted facts stay unknown'), but doesn't cover other alternatives (e.g. get_listing_truth, get_market_context) or failure conditions.

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, and destructiveHint=false, so safety behavior is covered. The description adds useful behavioral scope beyond annotations: only agencies with active listings are returned, and results include current buy/rent stock and asking-price ranges. It does not describe pagination or rate limits, but for a read-only query that is a minor gap.

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 description is a single front-loaded sentence with no wasted words. It states the resource, geographic constraint, and included data efficiently. Every clause 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 an output schema present and annotations covering safety and idempotency, the description provides enough purpose and result scope for a simple read-only lookup. It does not mention the optional locale parameter at all, though the schema covers it. Usage guidance against sibling tools is missing, but the core call semantics are 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%, so both commune and locale are already documented in the input schema. The description hints that commune must be a supported Luxembourg town, which aligns with the schema but adds no new syntax or format details. 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?

The description states a specific verb and resource: get every estate agency with active listings in a supported Luxembourg town. It also clarifies the included data (buy/rent stock and asking-price ranges). It does not explicitly distinguish itself from sibling tools like search_for_sale or get_market_context, 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?

The description gives context that the town must be supported and agencies must have active listings, but it provides no explicit when-to-use guidance or alternatives. It does not tell an agent when to choose this over search_for_sale, search_rentals, or get_market_context. This is implied usage only.

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 credit goes to the added context: 'The tool re-reads canonical public listing facts before display' tells the agent the rendered data comes from a fresh canonical read rather than cached search output. Remaining gaps are error behavior for stale or invalid IDs, which is not disclosed.

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: what it renders and its cardinality first, then the required workflow, then the freshness guarantee. Every sentence carries an operational fact and 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?

With an output schema present, return values need no explanation, and the description covers the prerequisite workflow and data provenance. It omits what happens when a supplied ID is no longer found during the canonical re-read, which matters given the tool explicitly re-validates before display.

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 locale, heading, and the listings array. The description nonetheless adds a meaningful constraint beyond the schema: IDs and match scores/reasons must be copied 'without alteration', reinforcing provenance and discouraging fabricated values.

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 ('Render ... results ... as an interactive MCP Apps photo carousel') with explicit scope (one to eight) and provenance (from a prior property search). An agent can distinguish this display tool from search and analysis siblings like search_vibe or compare_listings without opening 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?

'Call a search tool first, then copy its listing IDs and any returned match scores/reasons without alteration' gives a clear prerequisite and ordering that selects this tool over siblings. It does not name a when-not-to-use condition or an explicit alternative display path, so it falls short of the top band.

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, and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context: it returns candidate sets rather than guessing, widens quarter/village names to a parent, and caps precision at municipality-centre coordinates with no property-level accuracy. That precision caveat is exactly the kind of thing an agent needs before feeding results downstream.

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 short sentences, front-loaded with the core purpose and followed by the ambiguity and precision caveats; nothing is redundant. It is dense with useful information per sentence, though the final sentence compresses two distinct ideas (parent widening and coordinate precision) in a way that takes a re-read.

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?

An output schema exists, so return shape need not be described, and the description correctly focuses on behavioral nuance instead. With only 3 parameters it covers the ambiguity and precision dimensions well; the remaining gap is guidance on query formats and whether multiple candidates mean the caller must choose.

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 only 33% (only `locale` is documented in the schema), so the description should compensate more than it does. It does add real meaning for `country` ('can narrow ambiguous names'), but says nothing about acceptable `query` formats (name vs alias vs official ID) despite that being the sole required parameter. Baseline 3 is the ceiling given the coverage gap.

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 (resolve) and resource (Grande Région names, translated aliases, official locality IDs), which tells an agent exactly what class of problem this tool solves. It is clearly a geocoding/entity-resolution tool, distinguishable from all listed siblings. It falls short of 5 only because 'Grande Région' is domain jargon that a general agent may not parse without prior knowledge.

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 implied usage context — 'Country can narrow ambiguous names' and 'Return candidates instead of guessing' signal that this is the disambiguation path rather than a point lookup. However, there is no explicit when-to-use/when-not statement and no reference to alternatives (e.g., how this differs from search_for_sale or get_town_agencies, which also involve places).

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 safety (readOnly/idempotent/non-destructive), and the description adds real context beyond them: every result links the original agency listing, carries a latest re-sighting timestamp, and top results ship as image content blocks. It still omits pagination/result-window behavior (handled only in the shownListingIds schema note) and any rate or latency characteristics.

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 dense sentences that lead with the default scope and the cross-border opt-in before moving to result behavior. Every clause carries information, though the second sentence packs several output facts into one 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?

For a 21-parameter search tool with an output schema and full annotation coverage, the description supplies scope, the key opt-in flag, and result provenance/thumbnail behavior. Remaining gaps (paging via shownListingIds, includePhotos, limit) are secondary but not fully covered elsewhere.

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 24% across 21 parameters, so the description carries extra weight. It maps the filter categories (location, price, rooms, area, property type, amenities, sort) and explains includeCrossBorder, but leaves limit, includePhotos, locale, and the enum semantics of sort/parkingType unaddressed.

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 with scope: 'Search properties for sale in Luxembourg by default'. The 'for sale' qualifier implicitly separates it from search_rentals, but no sibling is named explicitly, so an agent must infer the boundary from the resource noun.

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 default Luxembourg scope and the includeCrossBorder opt-in give some routing signal, but there is no guidance on when to prefer this over search_vibe, get_listing, or search_rentals, nor on when to call resolve_location first (only the schema hints at 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?

Goes well beyond the readOnly/idempotent/openWorld annotations by disclosing that the strict ceiling drops listings with incomplete cost evidence, source freshness, or fees, and that results carry completeness metadata plus agency links and re-sighting timestamps. That is substantive behavioral context an agent could not infer from the annotations or schema, though return shape and pagination semantics remain unaddressed.

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 sentences, front-loaded with the searchable dimensions, followed by the two nontrivial behaviors. Dense but free of filler; 'positive-evidence amenities' and 'latest catalogue re-sighting time' are slightly opaque coinages but earn their space.

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?

An output schema exists so return values need not be explained, and the description correctly focuses on filter semantics and result completeness. The main shortfall is silent pagination - shownListingIds is a non-obvious paging mechanism for a 21-parameter search tool whose results are explicitly described as not a stable snapshot.

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?

Effective schema description coverage is only 24% across 21 parameters, so the description should carry more. It does add the highest-value distinction - advertised base rent (minPrice/maxPrice) versus a separate strict confirmed monthly-obligation ceiling (maxTotalMonthly) - and clarifies that amenity flags are positive-evidence only, but sort, limit, locale, includePhotos, parkingType, and shownListingIds receive no mention.

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 (search) and resource (active Luxembourg rentals) with the filterable dimensions enumerated, which distinguishes it from search_for_sale by geography/asset class. It never names an actual sibling tool, so an agent must infer the boundary with search_vibe, get_listing, and compare_listings rather than being told.

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 condition for using the strict ceiling versus the advertised base rent is implicit in the phrasing, and the exclusion behavior is described, but there is no explicit 'use this when...' or 'prefer X for Y' guidance. With 19 siblings covering overlapping territory (search_vibe, compare_listings, get_listing_truth), the absence of routing direction 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?

Goes well beyond the readOnly/openWorld annotations: it discloses that the 0-100 score is a request-fit score and not a probability, that degraded runs drop ranking claims, that every result links a source agency listing with a re-sighting time, and that unresolvable places yield zero listings plus a machine-readable reason instead of substitutes. These are the exact failure modes an agent needs to interpret output correctly.

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 one-line purpose, then layered with behavior, output semantics, and the unanswerable case. Dense and nearly waste-free, though the understanding/notChecked sentence is wordy and could be tightened.

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?

An output schema exists, yet the description still supplies what the schema can't: the meaning of the fit score, degraded-mode behavior, grounding guarantees, and how the understanding block should be read. For an open-world LLM-backed search tool this covers everything an agent needs to call it and interpret it safely.

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 baseline is 3. The description adds conceptual framing for `query` (prose, lifestyle/vibe) but says nothing about `brief`, `followUp`, `shownListingIds`, or `limit`, all of which are documented only in 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 and resource ('natural-language ... property search') and immediately explains the mechanism (embeddings + LLM reasoning over lifestyle, mood, proximity, soft preferences). This clearly separates it from the structured siblings search_rentals and search_for_sale 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?

'Preferred' signals this is the default for free-form requests, and the prose-matching framing tells the agent which kinds of requests belong here. However, it never names the alternatives (structured search_rentals, get_listing, resolve_location) or states when to fall back to them, so routing 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 signal mutation (readOnlyHint=false, destructiveHint=true), and the description adds concrete behavioral details: it either creates a conversation thread or returns agency contact details. This clarifies the side-effect nature beyond the raw hints, though it omits prerequisites like authentication or persistence guarantees.

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 description is a single, front-loaded sentence that efficiently conveys the primary action and the two possible outcomes. Every word adds value with no repetition of 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?

Given the output schema exists and annotations cover the safety profile, the description is complete enough for an agent to understand invocation intent and expected behavior. It could mention how to identify listing type, but that is likely available from listing data and not essential for tool selection.

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 four parameters. The description does not add parameter-specific meaning, but the baseline of 3 is appropriate since structured fields carry the semantic load.

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 action ('Submit an inquiry about a listing') and adds a meaningful behavioral distinction: chathome-hosted listings create a conversation thread, while external agency listings return contact details. This clearly differentiates the tool from siblings like get_inquiry_status and get_listing.

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 clear context for when to use the tool and how behavior changes based on listing type. It does not explicitly name alternatives or state when not to use it, so it stops short of a full 5.

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