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

With no annotations, the description carries the full burden and does well: it discloses upsert semantics, the search-then-create fallback order, partial-update behavior, and the hard rule that addresses must never be invented. It stops short of stating return shape, error behavior, whether a lookup match is ever ambiguous, or what the auth token must be, so it is strong but not exhaustive for a mutation tool.

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 the mutation type and field scope, then the two operational branches, then the replacement note — a logical ordering with no filler sentences. The parenthetical field list is partly redundant with the schema, which is the main thing keeping it from a 5.

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 14-parameter, annotation-free upsert with no output schema, the description covers the decisions an agent must get right: which mode to use, how matching works, and the address constraint. Missing pieces are secondary — return value, failure modes, and auth specifics — so it is complete enough to call correctly but not fully self-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?

At 50% schema coverage across 14 parameters, the description adds real meaning by grouping the business fields and, critically, explaining client_id's dual role (update target vs. trigger for search-and-create) — which the schema only hints at. It does not explain request_id idempotency or auth_token beyond a passing '(token)' note, but most parameters now have semantics from schema plus description combined.

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 precise verb pair and resource ('Crée ou met à jour un client Qonto') and enumerates the domain fields covered (nom, type, email, adresse, SIREN/SIRET, TVA, contact). It also names the sibling it supersedes ('Remplace qonto_update_client'), so an agent can separate it from qonto_update_client 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 explicit branching conditions: with client_id → targeted update of supplied fields only; without client_id → lookup by email, then name, then update-or-create. It also flags the prerequisite scope ('RÉSERVÉ AU STUDIO (token)') and the creation constraint that a complete, non-fabricated address is mandatory. The only gap is that the superseded qonto_update_client still appears in the sibling list, leaving a mild ambiguity about which to prefer.

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