CréaCompare

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real value beyond that: the result set is sorted by total estimated cost defined as service price plus legal fees, and each entry carries conditions, lead times, promotions, a verification date and a link. It does not mention the default page size behaviour beyond the 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 the purpose, second sentence listing returned fields. No padding or repetition of the title.

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

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

There is no output schema, and the description compensates by enumerating the returned fields and the sort key, which is what an agent needs to interpret results. Only the truncation/limit semantics of the result set are left 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?

Schema description coverage is 100% (both params documented, enum enumerated), so the baseline is 3. The description only restates that legal_form drives the comparison and says nothing about max_results or the default of 10 that the schema already carries.

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 ('Compare les offres des prestataires de création d'entreprise') plus the scoping unit (a legal form) and the sort order. It is clearly distinguishable from list_legal_forms and get_provider, though it never names the siblings to make the contrast explicit.

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 phrase 'pour une forme juridique' implies a legal_form identifier is needed, but there is no statement of when to call this versus list_legal_forms or get_provider, 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?

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context by listing the payload contents (description, live promotion, review page, offers per legal form), which is exactly what an agent needs to decide whether to call 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 sentence with zero filler, front-loading the verb and resource before the returned-field list.

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 partially compensates by enumerating the returned fields, which is adequate for a one-parameter read tool. Minor gap: it does not indicate response shape or ordering of the offers list.

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

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

Schema description coverage is 100% and the single parameter is a fully enumerated provider_id with an example, so the schema does the heavy lifting. The description adds no further semantics about the identifier, which is the correct baseline-3 outcome.

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+resource ('Renvoie le détail d'un prestataire de création d'entreprise') and enumerates what comes back (description, current promo, CréaCompare review page, all offers by legal form). That enumeration implicitly separates it from compare_offers and list_legal_forms, but 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: the single-provider scope and the 'detail' framing tell an agent this is the per-provider lookup, but there is no explicit when-to-use or when-to-prefer-compare_offers guidance. The enum of provider IDs constrains the call without explaining routing.

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

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is fully covered. The description adds genuine value by specifying what the call yields (associates count, liability, social regime, suitability, mandatory creation fees), which matters because there is no output schema. It does not state ordering or total count, a minor omission.

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

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

One sentence with no filler, front-loaded with verb and resource. The trailing enumeration of returned fields is dense but each item earns its place by describing output the agent cannot otherwise see. Slightly run-on but efficient.

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 input parameters, a fully annotated read-only profile, and no output schema, the description must carry the return-content burden and it does so by naming the attributes returned. Only the ordering/length of the returned catalog is left unstated, which is minor for a static reference list.

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 the baseline is 4; there is no parameter semantics to explain and the description correctly spends no words on inputs. Nothing in the description suggests configurable filtering that would create false expectations about a parameterless call.

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 opens with a specific verb and resource ('Liste les formes juridiques françaises') and enumerates both concrete examples (micro-entreprise, EURL, SASU...) and the attributes returned (associés, responsabilité, régime social, frais légaux). This makes the tool's output unmistakable. It does not explicitly differentiate from the siblings compare_offers/get_provider, but the resource domain is plainly distinct.

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 a reference/catalog lookup for legal form definitions, but there is no statement of when to call it versus compare_offers or get_provider, nor any prerequisite or exclusion. For such a simple read-only catalog tool that is adequate, but it leaves routing to inference.

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