branco

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

The annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds a small behavioral nuance with 'actuellement déclarés', suggesting a point-in-time snapshot, but it does not disclose other behavioral traits such as caching, cost, or potential staleness.

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 entire description is one compact sentence that front-loads the action and resource, then gives a dense but complete list of output categories. There is no filler or redundant restatement 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?

For a zero-parameter, read-only inspection tool, the description is complete: it identifies the subject, the output categories, and the snapshot-like nature of the result. An output schema exists to carry return-value details, so the description does not need to explain them.

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?

There are zero parameters, so the baseline is 4. The description compensates by enumerating the kinds of state information the tool returns, which gives an agent a useful sense of what to expect even though no input parameters need explanation.

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 ('Expose') and names the resource ('l'état des corpus') plus the concrete data categories it returns (versions, bornes, compteurs, retards, limites, alvéoles, garde-fou qualité). This clearly distinguishes it from the sibling search and citation-verification tools, which serve different purposes.

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 this is the tool to call when an agent needs a current snapshot of BRANCO's corpus state, but it does not explicitly state when to prefer it over the siblings or when not to use it. The usage context is inferable from the tool's purpose but not articulated.

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, and destructiveHint false, so the safety profile is covered. The description adds meaningful behavioral context beyond those annotations: it specifies that searches are performed locally, that the penal filter is intentionally broad, and that scope can be widened to the whole catalog or narrowed to a NOR number. 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 two sentences long, front-loads the core purpose, and includes only relevant scoping information. Every sentence earns its place and there is no repetition or 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?

Given five unannotated parameters, no schema descriptions, and no explicit guidance on combining requete, nor, and perimetre, the description is not complete enough for reliably correct invocation. The output schema covers return shape, but search construction and pagination semantics remain underspecified.

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%, so the description must compensate, but it only hints at two concepts: NOR numbers and the penal versus full-catalog perimeter. It does not explain requete, limite, offset, or how parameters combine, leaving the agent to infer most parameter semantics from parameter names alone.

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 identifies the action ('Recherche localement les notices de toutes les circulaires publiées en ligne') and the specific resource scope (criminal circulars in the Bulletin officiel du ministère de la Justice). It also explains the broad penal filter and the ability to search the full catalog or by NOR, which adds useful nuance. However, it does not explicitly contrast with sibling tools like decrire_etat_corpus or verifier_citation.

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 the tool: when searching for penal circulars, the full catalog, or by NOR number. It gives a sense of scope but provides no explicit when-not-to-use guidance or mention of sibling alternatives, leaving some routing decisions to inference.

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 idempotentHint=true. The description adds behavioral depth by specifying local execution ('localement') and the normalization of case, spaces, and typographic signs. It also discloses the negative scope. These go beyond the annotations without contradicting them.

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 with zero fluff. The main action is front-loaded, and the limitation is stated immediately after. Every word earns its place; there is no 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?

With an output schema present, return values are covered. The description gives purpose, normalization behavior, and limitations. It does not explain the 'longueur_contexte' parameter or its effect on the output, which is a minor gap, but for a simple verification tool the description is largely sufficient.

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 texte_source has a schema-level description). The tool description gives no explicit guidance on parameters 'citation' or 'longueur_contexte'. While the description implies what a citation/text is, it fails to compensate for the low schema coverage, especially for the optional context-length 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 states a specific verb ('Contrôle'), a clear resource ('si une citation figure dans un texte fourni'), and adds the normalization detail. It also clarifies boundaries by stating what it does not validate (authority, relevance, legal meaning). This clearly distinguishes it from siblings like decrire_etat_corpus and rechercher_circulaires_penales.

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 provides clear context: it checks material presence, not semantic validity. The negative scope ('Ne valide ni l’autorité...') implicitly tells the agent when not to use this tool. However, it does not name alternatives or explicitly state 'use this when...', leaving some inference to the agent.

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