Apparais

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

The readOnlyHint and openWorldHint annotations already establish that this is a safe, closed-world read operation. The description adds that the output is a concrete, prioritized checklist spanning Google Business Profile, reviews, directories, website, and structured data, which helps set expectations. It still lacks detail on output structure, length, or how the optional metier changes the checklist, so it earns a 3.

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?

It is one tightly written sentence with no filler, and the key qualifiers (“concrète et priorisée”) are front-loaded. The parenthetical topic list is compact and informative.

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, non-mutating, single-optional-parameter tool with no output schema, the description gives enough to know what the tool returns and what domains it covers. Minor gaps remain around output format and how metier customizes results, but overall it is complete enough.

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

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

Schema description coverage is 100%; the single optional metier parameter is already documented as “Métier (optionnel), pour adapter les conseils”. The description does not mention the parameter or add any semantics beyond the schema, so the baseline of 3 is appropriate.

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

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

The description names the deliverable (a concrete, prioritized checklist) and the exact outcome and channels it covers: Google Maps/ChatGPT recommendations, Google Business Profile, reviews, directories, website, and structured data. That is clear, but it never contrasts with siblings such as tester_mon_commerce or classement_chatgpt, so it stops short of a 5.

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

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

It implies the use case (helping a local business be recommended on Google Maps and ChatGPT) but gives no explicit when-to-use or when-not-to-use guidance. It also never names alternatives like tester_mon_commerce, so the agent must infer that this is the guidance/checklist tool rather than the testing or ranking tools.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description usefully adds that the ranking comes from a periodically refreshed dataset ("mis à jour régulièrement"), which explains the non-live, non-open-world behavior. It also discloses what the response contains conceptually — citation share per business and the sites ChatGPT consults. It stops short of stating freshness guarantees, coverage limits, or whether a missing city returns empty versus error.

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

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

One dense sentence, front-loaded with what is returned, followed by the data source and the returned metrics. No filler or repetition; the parenthetical about the source is well-placed rather than buried.

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

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

With only two required parameters, no nested objects and no output schema, the description covers what is needed: what comes back, that it is a ranking, and the metrics included. Gaps are secondary — list size, pagination, and empty/unknown-city behavior are unspecified, but an agent can still call it correctly.

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

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

Schema coverage is 100%, so both parameters (ville, métier) are already documented with examples, and the baseline of 3 applies. The description adds only the constraint that the city must be French and reinforces the métier framing, without normalizing expected input format or listing supported 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?

The description gives a specific verb+object ("Renvoie les commerces que ChatGPT recommande le plus") scoped to a métier in a French city, and even names its data source (classement Apparais). It is clearly understandable without opening the schema, but it never differentiates itself from siblings such as liste_classements or checklist_visibilite_locale, which an agent would need to pick between.

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 or when-not-to-use guidance, and no sibling is named as an alternative. The only implicit signal is the métier/ville scoping, which tells the agent what inputs are needed, not when this tool is the right choice over liste_classements or tester_mon_commerce.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the agent knows this is a safe, closed-world read. The description adds a genuine scope constraint by limiting results to already-published rankings, but says nothing about ordering, pagination, or size of the result set. Useful but not rich behavioral 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?

A single front-loaded sentence with the verb and resource first, and the filtering clause last; nothing is redundant. Minor awkwardness from the product token "Apparais" embedded mid-phrase slightly hurts readability.

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-only listing tool with full schema coverage and no output schema, the description covers what the tool returns (published rankings keyed by métier × ville) and how to narrow it. Only the result shape and volume remain unstated, which is a small gap 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% and both parameters (ville, metier) are already documented as optional filters in the schema. The description repeats that the list is filterable by city or métier but adds no syntax, matching behavior, or combination semantics beyond the schema, 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 ("Liste") and resource ("classements Apparais déjà publiés") plus the ranking key ("métier × ville"), so the agent knows exactly what is returned. It does not explicitly name or contrast with any sibling tool such as classement_chatgpt or checklist_visibilite_locale, which keeps it from a 5.

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

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

Usage is only implied: the tool is for browsing existing published rankings, and "déjà publiés" hints that unpublished or to-be-generated rankings are out of scope. There is no explicit "use this when… / use sibling X instead…" guidance, so the agent must infer routing from the sibling names alone.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond them: the result arrives in about 30 seconds, no bank card is required, and the output is a link rather than a report body. It does not say whether the test is persisted or whether repeat calls regenerate it, which would have completed the picture.

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

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

One dense sentence that front-loads the deliverable (the link) and then justifies it with the test's contents and the speed/no-card guarantees. No filler, though the colon-separated list of test dimensions is packed tightly enough to be slightly harder to scan.

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

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

With no output schema, the description correctly compensates by stating that the return value is a link and how long it takes. For a three-parameter read-only tool with full schema coverage, this is close to sufficient; only the persistence/regeneration behavior is unstated.

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

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

Schema description coverage is 100%, so all three parameters are already documented in the schema, and the baseline is 3. The description adds only the notion that the target is a specific business; it never mentions 'ville' (required) or the optional 'metier', so it adds no meaning beyond the structured fields.

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: it returns the link to the free 'Apparais' test for a given business, and enumerates what the test contains (ChatGPT score over 10 customer questions, competitors ranking ahead, Google listing score). It is clear enough to distinguish from a generic listing tool, but it never names the siblings (classement_chatgpt, checklist_visibilite_locale) whose subject matter overlaps most, so the boundary is left to inference.

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 by 'pour un commerce précis' and by the promise of a free, no-credit-card test. There is no explicit statement of when to call this rather than classement_chatgpt or checklist_visibilite_locale, 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.