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

Annotations already cover the read-only, idempotent, closed-world safety profile, and the description goes well beyond them: result fields returned (article number, instrument title, official excerpt, PDF link, score), the 0.40 relevance threshold, corpus size and snapshot date (2026-10-05), data source and licence, and the explicit statement that no generated answer is produced.

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 core ('Recherche sémantique, article par article') is front-loaded and each sentence carries information; nothing is padding. However, the full bilingual duplication roughly doubles the length for an audience that the schema already serves in both languages.

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, the score threshold, and the corpus provenance. Combined with annotations covering safety and a fully documented 4-parameter schema, an agent has everything needed to 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 the baseline is 3; the description adds real meaning on top by advising when to supply `pays` ('quand il est connu') and by framing `query` as a question or topic. It says little about `limit` or `objet` beyond what the enum and bounds already convey.

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 with scope: 'Recherche sémantique, article par article, dans les 237 actes des conventions fiscales conclues par la France'. It also names the sibling to use next (conventions_article) and explicitly disclaims generating an answer, so an agent can separate it from bofip_search or legifrance_article without opening a schema.

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?

Gives concrete invocation guidance: 'Préciser `pays` quand il est connu' and 'Lire ensuite l'article avec conventions_article', plus the note that an explicit reference like 'article 18 Suisse' is resolved directly. It lacks an explicit when-not-to-use / alternative-for-broader-search statement, which keeps it short of a 5.

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