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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, but the description adds a meaningful data-disclosure guarantee: it returns only id, prénom, initiale du nom, visites, dernière visite and card state, and "jamais d'e-mail ni de téléphone". That privacy boundary and the pagination/tri behavior are genuine additions. It stops short of 5 because it says nothing about volume limits beyond pagination or about empty-result behavior.

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?

Front-loaded with purpose, then filters, then return shape, then usage — a sensible order with no filler sentences. It runs long as a single dense block and re-enumerates the segment list that the schema already defines, which is redundant for an agent that reads schemas.

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 17 optional parameters and no output schema, the description carries the burden well: it discloses the exact fields returned, the privacy exclusions, and how sorting/pagination apply. Nothing material an agent needs to call this correctly is missing.

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 100%, so the baseline is 3. The description names the filter dimensions (prénom, tampons, visites, dates, wallet) and glosses the segments in human terms ("habitués, perdus de vue, à un tampon..."), which helps map colloquial phrasing to enum values, but it adds no syntax or semantics beyond what the enum descriptions already spell out in detail.

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?

Opens with a specific verb ("Liste") and resource ("les clients du commerce"), then states the two axes it operates on: segment and filters, plus sorting and pagination. It also distinguishes itself from fiche_client by positioning itself as the way to obtain a client identifier first, so an agent can route without opening either 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 trigger questions ("qui sont mes meilleurs clients ?", "qui n'est pas revenu ?", "qui est proche de sa récompense ?") and an explicit downstream handoff ("retrouver l'identifiant d'un client avant fiche_client"). This is real when-to-use guidance plus an alternative-tool routing rule, not implied usage.

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