DéclaClic : panneaux solaires

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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description adds scope boundaries beyond that: French jurisdiction, existing house roofs, and the specific procedural facets covered. It does not describe output form or any depth limits, which keeps it from a 5.

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 naming the domain first, then a compact list of covered topics. Every clause carries information; the trailing 'service DéclaClic pour la préparer' is the softest element but still signals a concrete named procedure.

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 knowledge-retrieval tool with no parameters and no output schema, the description is sufficient: it fixes jurisdiction, housing type, and the procedural facts an agent can expect. It stops short of stating what an answer looks like or the limits of the knowledge (e.g. regional variations, recours timelines), which keeps it at 4.

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 and the schema is empty and fully closed (additionalProperties: false), so there is nothing for the description to disambiguate. Baseline of 4 applies for a parameter-free tool; nothing in the text misleads about inputs.

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 concrete resource ('Règles de la déclaration préalable de travaux pour des panneaux solaires sur le toit d'une maison existante en France') and enumerates the coverage areas (obligation, Cerfa 16702, pièces DPC, délais, recours, DéclaClic). Scope is narrowed to existing houses in France. It does not explicitly contrast with the sibling 'verifier_adresse_panneaux_solaires', so differentiation is only implicit.

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?

Use is only implied: an agent can infer the tool is for questions about rooftop solar permit rules. 'Quand elle est obligatoire' describes the content returned, not when to invoke the tool. There is no explicit exclusion (e.g. new-build, ground-mounted panels) and the sibling tool is never mentioned as an alternative.

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 open-world, so the safety profile is covered. The description adds behavior beyond that: the data are public and indicative, and the agent is told to foreground for the user what remains 'à vérifier' — a real presentation caveat not encoded anywhere else. It stops short of stating data sources' freshness limits or failure behavior for unmatched addresses.

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?

Scope is front-loaded in the opening clause, then the returned data are enumerated, then the 'indicative data' caveat closes it. It is a single dense sentence with no filler, though the mid-sentence list of six outputs makes it slightly run-on.

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 tool with no output schema, the description usefully enumerates what comes back (cadastral parcel, PLU zone, heritage protections, required documents, instruction deadline, DéclaClic link), so an agent can decide whether to call it. What is missing is the sibling disambiguation and any note on how the response is organized.

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 is a single parameter with 100% schema description coverage, so the schema already defines the full postal address format. The description only adds the framing 'à partir de cette adresse', which gives no extra semantic detail (no normalization rules, no partial-address handling). Baseline 3 applies when the schema carries the burden.

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 concrete resource set the tool resolves for a given address: parcelle cadastrale, zone du PLU, protection patrimoniale, pièces de la déclaration préalable, délai d'instruction, plus a DéclaClic link. It also fixes the scope('maison en France métropolitaine', solar panels on the roof), so an agent knows exactly what the call produces. It never mentions or contrasts with the sibling demarche_panneaux_solaires_toiture, which is the one missing clarity element.

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 context is present and fairly specific: an individual homeowner in metropolitan France wanting rooftop solar panels. There is no explicit when-not guidance, no prerequisites about address quality beyond the schema, and no routing between this tool and the sibling, so the agent must infer the choice between checking an address and running the procedure.

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