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

With no annotations provided, the description carries the full transparency burden. It discloses key behaviors: SIRET ignores other parameters and returns all inspections sorted by date descending, data refresh frequency is periodic, and only controlled establishments since 2017 are covered. There is a minor inconsistency between 'real time' (English) and 'refreshées périodiquement' (French), but overall the behavioral disclosure is strong.

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 information-dense and logically structured: it opens with the main purpose, enumerates returned data, then explains search modes and coverage. The English translation adds length by repeating the French content, but it does not clutter the core message. It is slightly redundant but not wasteful.

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 the tool's complexity (5 optional parameters, no output schema, no annotations), the description provides a thorough picture: what the tool returns, how to search, which parameters to combine, what data is covered, and update cadence. This is sufficient for an agent to select and invoke the tool correctly in most scenarios.

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 descriptions already cover all 5 parameters in detail (100% coverage), which sets a baseline of 3. The tool description adds value beyond the schema by recommending SIRET as the preferred search key, advising combination of 'nom' with 'code_postal' or 'commune' for disambiguation, and clarifying that SIRET overrides other parameters. This extra guidance raises the score to 4.

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 states the tool's function with a specific verb ('Recherche') and a precise resource ('score Alim'confiance d'un établissement précis dans le dataset officiel de la DGAL'). It lists the return fields and explicitly mentions the dataset source and record count, distinguishing it from sibling tools like get_score_alimconfiance by focusing on a specific establishment lookup.

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 usage guidance: recommends SIRET as the unique identifier, explains when to use name search with optional postal code/commune filters for disambiguation, and notes the data coverage (only establishments inspected since April 2017). However, it does not explicitly contrast this tool with sibling tools or state when not to use it, so it stops short of a full 5.

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