BankLabs

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

With no annotations, the description carries the full burden and does disclose two non-obvious behaviors: the overloaded fallback response (profiles list when profile is omitted) and the rule that unknown line items are never counted as 0 €, guarding against silent underestimation. It omits currency, whether results are point estimates or ranges, and read-only/rate-limit 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?

Three short sentences, front-loaded with the core purpose, followed by the fallback rule and the estimation caveat. 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?

Adequate for a two-parameter read tool, but with no output schema the description never says what the returned costs look like (per-bank totals, breakdown by fee category, currency, ranges), which is the main thing an agent needs to interpret 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 coverage is 100%, so the schema already documents both parameters and even enumerates example profile IDs. The description only restates that banks are 'several' and that the profile must be explicit; the useful profile-omission behavior is behavioral rather than parameter-level detail.

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: estimated annual cost for several banks given an explicit usage profile, which distinguishes it from the sibling compare_banks (generic comparison) by the cost/profile framing. It does not explicitly name the alternative, so it stops short of 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?

Gives concrete usage context: a profile is required for meaningful results, and if none is supplied the tool instead returns the list of available profiles. It does not explicitly route the agent to siblings like get_bank_fees or get_fees_barometer for raw fee data, so no exclusion 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?

With no annotations, the description carries the full burden, but it does disclose the return format (Markdown) and the URL/slug convention ('-vs-'), which implies a read-only operation. It says nothing about behavior for invalid or duplicate slugs, or whether the response is page content versus a reference to 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?

A single front-loaded sentence with no filler; the core action and the slug-joining convention both land 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 read tool with no output schema, the description covers the action and return format adequately. It leaves unresolved whether the result is rendered page content or a path/URL, and how missing slugs are handled.

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 parameter's ordering semantics are already documented in the schema. The description's 'two or three' merely restates minItems/maxItems, adding little beyond the structured field.

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 ('Return the Markdown comparison page') plus the slug convention, so the agent knows exactly what it gets. It does not distinguish itself from siblings like get_page_markdown or compare_annual_cost, which is the main gap.

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 and no named alternative, despite plausible siblings (get_page_markdown for a single page, compare_annual_cost for cost comparisons). The agent must infer the use case entirely from the name and 'two or three' phrasing.

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?

No annotations are supplied, so the description carries the full burden; it partially meets it by declaring 'Lecture seule' (read-only) and by disclosing that the payload carries source and collection-date provenance. It says nothing about error behaviour, rate limits, or freshness beyond the collection date, leaving the mutation-safety and failure-mode picture incomplete.

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 naming the resource and its sections, followed by a short safety marker. Nothing is padded or repeated. The parenthetical list is dense but earns its place by describing the returned sections.

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 the return payload, and it does so by enumerating the fee categories plus source and collection date. Combined with the schema's documented valid_ids fallback, an agent has enough to call it correctly; only cross-tool positioning 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 a single parameter at 100% schema coverage, the schema already documents bank_id fully, including the slug format and the valid_ids fallback for unknown ids. The description adds no further meaning about that parameter, 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 names the specific resource (a bank's structured fee schedule) and enumerates its sections (account maintenance, card, incidents, foreign, intervention commission) plus the provenance fields (source and collection date). That is far more concrete than the title alone. It does not, however, distinguish this from siblings such as get_fees_barometer or get_tariff_changes, so the agent must infer the split.

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 retrieving one bank's full tariff sheet. There is no explicit statement of when to prefer it over compare_banks, get_fees_barometer or get_fee_history, and no prerequisites or exclusions are given.

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?

No annotations are supplied, so the description carries the full burden, and it does disclose what the response covers, including the unusual signals of source contradictions and next-year grid presence. It stops short of stating read-only semantics, auth requirements, or whether coverage is reported per-attribute or as counts.

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 compact sentences, with the resource definition front-loaded before the enumeration of contents and the usage trigger. The middle enumeration is dense but every item conveys distinct value; only the slightly clipped phrasing keeps it from a 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?

For a single-optional-parameter meta tool with no output schema, the description does the necessary work by enumerating the content categories an agent will receive, standing in for a return-value spec. It leaves the response shape (per-attribute detail vs summary) implicit.

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 optional parameter and 100% schema description coverage, the schema already explains the slug-or-entity-id convention and the omit-for-all behavior. The description only echoes the '(ou toutes)' default, adding no formatting 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 resource and verb: coverage metadata for a bank, naming the exact categories returned (documented attributes, official sources, missing attributes, source contradictions, next-year grid presence). This clearly separates it from data-fetching siblings like get_bank_fees or get_evidence, 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?

Gives an explicit trigger condition: call it before asserting that a datum does not exist. That is a clear usage context, but it offers no when-not guidance and does not contrast itself against alternatives such as get_evidence, which an agent comparing tools must infer.

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?

With no annotations, the description carries the full burden, and it does add real value by enumerating what the evidence payload contains: source type, effective date, collection date, page, exact excerpt and known contradictions. It does not state that the operation is read-only, nor anything about rate limits or failure behavior, leaving gaps that annotations would normally cover.

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 compact sentence that front-loads the subject and then lists the payload fields via a colon. Every listed item contributes to the reader's understanding; only the lack of an action verb costs it 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?

For a one-parameter read tool with no output schema, describing the return contents is the most useful thing the description can do, and it does so. It still omits the basic purpose statement and usage routing, and the French text sits oddly against English sibling names, so it is adequate rather than 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 coverage is 100% and the schema already explains that observation_id comes from get_fee_history (champ id). The description adds no additional meaning about the parameter, 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 names the resource ('Preuve d'une valeur') and enumerates the evidence components, so an agent can infer it retrieves the provenance of a value. However, no verb states the action ('retourne', 'récupère'), and it does not differentiate itself from siblings such as get_fee_history or get_tariff_changes, which also deal with fee data.

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 guidance and no alternatives are named. The implicit framing ('preuve d'une valeur') suggests it is used to verify or justify a figure, but the agent must infer that it is the follow-up to get_fee_history from the schema rather than from the description.

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?

With no annotations, the description carries the full burden and does disclose some useful behavior: results aggregate all sources, the optional date returns values in force at that date, and responses identify the regional entity for mutualist groups. It says nothing about ordering, response shape, or what happens with missing fee data, so the mutation/read and error profile remains unstated.

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 compact sentences, front-loaded with the core action and followed by the one genuinely non-obvious caveat about mutualist groups. No filler, though the second sentence is cryptic without domain knowledge of 'caisses régionales'.

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?

A four-parameter, no-output-schema tool that needs the description to explain returns. It conveys the gist (history + in-force value + entity attribution) but leaves the response structure, ordering, and behavior for unknown attributes unexplained; the schema does cover the unknown-key fallback, which offsets some of the 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%, so the baseline is 3. The description corroborates the optional date semantics ('valeur en vigueur à une date optionnelle') but adds no meaning beyond the schema for bank, plan, or attribute.

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 history of a single fee for a given bank) plus scope qualifiers ('toutes sources confondues', optional in-force date). It clearly implies a historical view as opposed to a current-fee lookup, though it never names the sibling tool it contrasts with (e.g. get_bank_fees or get_tariff_changes).

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: 'Historique' suggests choosing this over a current-fee tool when past values matter, and the mutualist-group note hints at when entity resolution matters. There is no explicit when-to-use / when-not statement and no named alternative among the ten siblings.

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?

No annotations are supplied, so the description carries the full burden; it does disclose 'Lecture seule' and mentions provenance fields (sources, collection dates), which is useful behavioural context. It says nothing about what happens with an unknown or outdated slug, whether missing editions error or return empty, or about result volume.

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 compact and front-loaded: the resource and its contents come first, then the exclusions, then the read-only note. No redundant sentences, though the term 'limites' is left unexplained and mildly dilutes the precision.

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-optional-parameter read tool this is close to sufficient, and it partially compensates for the absent output schema by listing the kinds of content returned. However, with no output schema and no annotations, the description should say more about the shape of the response and the no-argument default behaviour.

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 parameter already documents the slug format and the omit-for-latest default. The description adds no meaning beyond that, which is acceptable given the schema does the work, but it also does not clarify edition-selection semantics from its own text.

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: an archived edition of bank fees containing fixed statements, sources, collection dates and limits. It is clearly distinguishable from current-rate and total-cost tools, although the resource is stated as a noun phrase rather than with an explicit retrieval verb and no sibling tool is named.

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 negative guidance: 'Ni tarifs actuels ni coût total du compte' rules out the current-tariff case and the annual-cost case, which are exactly what siblings get_bank_fees and compare_annual_cost cover. It does not name those siblings or state the positive condition (for example, 'use when you need historical provenance').

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?

With no annotations supplied, the description carries the full behavioral burden. It does add one meaningful constraint — only *public* pages are fetchable, implying no authentication and that private or unpublished content will fail — but it says nothing about response size, truncation, caching, or error behavior for invalid paths.

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 is front-loaded with the verb and resource, with the page-type enumeration tacked on compactly. It is efficient and wastes no words, though the parenthetical list partially duplicates the schema's path documentation.

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 fetch with no output schema, the description is nearly sufficient: it names the input shape and states the return form (Markdown rendering). The only real gap is the absence of any hint about the response structure (front matter, headings) or failure modes, which is minor at 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 100% and the single `path` parameter is fully documented in the schema, including the exact route patterns for each page type. The description's parenthetical page list largely restates that schema content, so it adds little meaning beyond it; 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 (fetch) and a specific resource (the Markdown rendering of a Banklabs page), and enumerates the page categories covered (homepage, hub, fiche, comparatif, guide). This clearly separates it from the sibling tools, which all return structured data (fees, banks, promotions) rather than rendered page content, though no sibling is named 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?

Usage is only implied: an agent can infer this is the tool for retrieving raw page content, as opposed to the structured-data siblings. There is no explicit statement of when to prefer this over get_bank_fees or get_coverage, and no note on what to do if the page does not exist or if a structured tool would answer the question better.

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?

No annotations are supplied, so the description carries the full burden. It does add genuine behavioral value by disclosing data-provenance behavior: amounts not re-verified against a promotional source are flagged ('Les montants non relus sur une source promotionnelle sont signalés'). It does not state that the operation is read-only, nor anything about result ordering, volume limits, or how the flag is surfaced in the response.

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 compact sentences with no filler, and the core resource definition is front-loaded before the data-quality caveat. Slightly dense phrasing in French with the purpose clause embedded mid-sentence, but nothing that could be cut without losing meaning.

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 two-optional-parameter read tool with no output schema, this covers the essentials: what is returned, the granularity, the history toggle's purpose, and a caveat about data verification. The remaining gap is that it never says the tool is non-mutating or describes the shape of the returned records, but that is modest given the tool's simplicity.

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 baseline is 3; the description lifts it slightly by explaining the purpose of the history dimension ('pour juger si une offre actuelle est élevée'), which gives the include_history flag a rationale beyond the schema's mechanical 'true pour toutes les observations'. It still adds nothing about slug format for 'bank' beyond what the schema states.

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 (welcome bonuses / primes de bienvenue) and its grouping granularity ('par banque et offre'), plus a secondary capability (history for judging whether a current offer is high). It is clearly distinct from fee-oriented siblings like get_fees_barometer or get_bank_fees, though the verb is only implied by the tool name 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 by the phrase 'avec l'historique pour juger si une offre actuelle est élevée', which tells the agent the history exists for comparison purposes, and the schema notes include_history defaults to false. However, there is no explicit statement of when to call this versus sibling tools such as compare_banks or get_evidence, and no exclusion criteria.

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?

No annotations are supplied, so the description carries the full behavioral burden. It does useful work by enumerating the change categories and confirming this is a detection/read operation rather than a mutation, but it omits the comparison baseline (which two editions), default time window, and any pagination or volume expectations.

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 resource and the qualifying detail front-loaded; no filler. The parenthetical enumeration earns its place by telling the agent what kinds of changes to expect, though the sentence is grammatically 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?

With no output schema and no annotations, the description should cover more: both parameters are optional, yet the default comparison window and the shape/magnitude of results are unstated. It is adequate for a two-filter read tool but leaves a real gap around defaults.

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 schema already documents 'bank' (slug or entity id, omit for all) and 'since' (ISO minimum effective date). The description only restates that results are filterable by bank and date, adding no format or edge-case detail beyond the schema — 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 the resource precisely ('changements de tarifs détectés entre deux éditions d'une même source') and even enumerates the change kinds returned (hausse, baisse, gratuit/payant, conditions modifiées), so an agent can tell it apart from get_bank_fees or get_fee_history. It stops short of naming those siblings explicitly, so it is clear but not fully self-differentiating.

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 phrase 'détectés entre deux éditions' — the agent can infer this is for delta/churn questions rather than current-fee lookups. However, there is no explicit when-to-use versus get_fee_history or get_bank_fees, and no statement of what happens if 'since' is omitted (which editions are compared by default).

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?

No annotations exist, so the description carries the full disclosure burden; it does say the output is Markdown and that entries carry canonical fiche URLs, which is useful return-content context. It says nothing about ordering, list size, pagination, or whether the catalogue is complete, which matters for an unfiltered enumeration 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 sentence with the resource and the notable return detail front-loaded, and no filler. Nothing could be trimmed without losing 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 zero-parameter read tool with no output schema and low complexity, the description covers what is returned (banks plus canonical fiche URLs) in the stated format. Only secondary operational details like ordering or result-set size are absent, which is a minor gap at 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?

The tool takes zero parameters, so there is no parameter meaning to convey and the baseline of 4 applies. The input schema is an empty object with additionalProperties false, consistent with the description's no-argument framing.

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 a specific verb and resource ("List banks tracked by Banklabs") and adds what each entry contains (canonical fiche URLs in Markdown), which separates it from siblings such as compare_banks or get_bank_fees. It stops short of naming an alternative explicitly, so it is clear but not fully differentiated.

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 stated prerequisites, and no reference to any sibling tool. The enumeration intent is only implied by the verb "List", leaving the agent to infer that this is the discovery entry point before calling compare_banks or get_bank_fees.

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