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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine value by disclosing what data comes back per brand (parrain/filleul advantages, code, condition, verification date, fiche URL). It says nothing about behavior with unknown or duplicate brand names, which is the only remaining gap.

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 dense sentence, front-loaded on the verb and cardinality, with every clause carrying information (scope, resource, returned fields). No filler and nothing buried at the end.

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 no output schema, the description carries the return-value burden and does so by enumerating the compared fields; annotations handle the safety profile. Only the response shape (table vs list) and handling of unrecognized brands are unaddressed.

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?

With one parameter at 100% schema coverage, the baseline is 3. The description adds meaning beyond the schema by scoping the array to 'marques de l'annuaire', i.e. brand names drawn from the directory, which is a real constraint on valid values rather than a restatement of minItems/maxItems.

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 (Comparer) and resource (marques de l'annuaire Meilleur Code Parrainage), and pins the operating range to 'de 2 à 5 marques', which implicitly separates it from the single-brand detail_offre and the search-oriented rechercher_offres. It also enumerates exactly what is compared (filleul/parrain advantages, code, condition, verification date, fiche URL).

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 2-to-5 bound implies 'use this when comparing several brands and not one', but the description never states when to prefer it over detail_offre or rechercher_offres, nor any exclusion. Usage is inferable rather than explicit.

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