index

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals key non-obvious traits: the score is 'publié' (not computed live), it reflects what an AI assistant can read without executing JavaScript, and it includes the measure's limitations. It stops short of describing error behavior, authorization needs, or side effects, but the read-only nature is clearly implied.

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 compact and front-loaded: the first part states the core purpose immediately, and the second part lists additional return contents without fluff. Both sentences earn their place, and the text is appropriately sized for a simple one-parameter tool.

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

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

For a low-complexity tool with one parameter and no output schema, the description is remarkably complete: it states the input, the core return value, the additional returned fields, and the measurement limitations. There is no overlooked operational aspect that an agent would need to call this tool 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?

The schema already covers 100% of the single parameter 'domaine' with an example, so the baseline is 3. The tool description reinforces the role of the parameter by tying it to the domain whose score is returned, but it adds no additional format, validation, or usage 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 states a specific verb and resource: it returns the published Agent Readiness Score for a domain, and clarifies what that score represents by adding the limitation 'sans exécuter de JavaScript'. It also enumerates the returned information (detail par axe, date, barème, ce que la mesure ne dit pas), making its purpose concrete and distinguishable from sibling tools like 'ce_qui_manque'.

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 intended use is implied: call this when you need the published Agent Readiness Score for a given domain and its breakdown. However, it does not explicitly state when to prefer this tool over its siblings, such as 'ce_qui_manque' or 'secteur', nor does it provide any exclusion conditions or alternative 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?

No annotations are provided, so the description carries the full burden. It discloses that the domain must be published and that the output includes quantified findings and purchase questions that no page answers, suggesting a read-only analysis tool. However, it does not cover failure behavior, data freshness, or what happens when the domain is unpublished.

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 dense sentence that leads with the verb and resource, then lists the three output components. There is no filler, though the phrase about 'questions d'achat auxquelles aucune page ne pourra jamais répondre' is somewhat elaborate.

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 tool with no output schema and no annotations, the description gives a reasonable outline of the return payload: weak axes, quantified evidence, and purchase questions. It leaves gaps around valid domain values and error behavior, but the low complexity makes this acceptable.

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 0%, and the description only indirectly defines 'domaine' as a published domain. It provides no format, allowed values, or reference to a sibling tool like secteurs_disponibles for valid inputs. The description adds minimal semantic value for the single parameter.

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

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

The description uses a specific verb 'Rend' (returns) and identifies a concrete resource: the weakest axes of a published domain, along with quantified evidence and purchase questions. This makes it distinguishable from siblings like 'secteur' or 'secteurs_disponibles', though it does not explicitly name them.

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

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

There is no guidance on when to use this tool versus agent_readiness, secteur, or secteurs_disponibles. It implies the tool applies to a 'domaine publié' but does not state prerequisites, exclusions, or how to obtain a valid domain value. An agent must infer context from the name and sibling list.

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

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

No annotations are provided, so the description carries the full burden. It adds useful behavioral details: results are grouped by level and scores within 5 points are not differentiated. Still, it does not describe return fields, empty results, invalid sector handling, or any data limits.

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 with no filler. The main behavior is front-loaded, and the second sentence adds a meaningful tie-breaking rule. Every sentence 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?

For a simple one-parameter retrieval tool, the description gives enough to invoke it correctly: the grouping structure and the scoring nuance. The main gap is the absence of an output schema or field-level explanation, but sibling secteurs_disponibles helps supply valid parameter values.

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 description coverage is 100%, and the sole parameter 'secteur' already includes examples. The tool description adds no additional meaning 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 uses a specific verb ('Rend') and a clear resource ('les sites publiés d'un secteur') with an explicit grouping behavior ('groupés par niveau'). It is easy to distinguish from siblings like secteurs_disponibles, which likely lists sectors rather than ranked sites.

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 intended use is implied: call this tool when you need a sector's published sites grouped by level. However, the description does not state when to prefer this over siblings such as secteurs_disponibles or ce_qui_manque, nor does it mention any exclusions.

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

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

With no annotations available, the description carries the behavioral burden. It discloses the inclusion/filter behavior (only sectors with at least one published company), but does not mention return shape, ordering, or side effects. This is acceptable for a zero-parameter list operation but not richly transparent.

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. Every word contributes meaning, and it avoids repeating the tool name or 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?

For a zero-parameter listing tool, the description is nearly complete: it names the resource, the operation, and the availability filter. It stops short of describing the exact return representation of a 'secteur', but the absence of parameters and output schema limits 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?

The input schema has no parameters and schema coverage is effectively complete at 100%, so there is nothing for the description to add. Per the zero-parameter baseline, a score of 4 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 uses a specific verb ('Liste') and a clearly scoped resource ('secteurs comptant au moins une entreprise publiée'). It is immediately distinguishable from the sibling 'secteur' by its plural scope and availability criterion, even though the sibling is not 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?

No guidance is given about when to choose this tool over siblings such as 'secteur' or 'ce_qui_manque'. The selection criterion is implied but no explicit context, prerequisites, or exclusions are provided.

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