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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds what the schema cannot: results include price (TTC), variants and availability, and results are cursor-paginated. The 'Lecture seule' sentence merely restates the annotation, so it adds some context but with minor redundancy.

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 on the core verb and scope, with the usage condition and example following naturally. Every clause except the trailing 'Lecture seule' nudges the agent toward correct invocation; the paragraph is dense but not padded.

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?

Even without an output schema, the description tells the agent what comes back (products, prices in TTC, variants, availability) and that results are paginated via cursor. The only material omission is the localization/context object, which the schema itself documents.

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 description reinforces the text and filter parameters (categories, price thresholds) and mentions the pagination cursor, but says nothing about the context/localization object (currency, language, address_country) despite that being a top-level parameter. With schema coverage at 75%, the description compensates only partially.

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 (Recherche) and resource (produits dans le catalogue PUBLIC du marchand), with scope qualifiers (texte libre, filtres facultatifs). The clause about not having a product identifier implicitly separates it from get_product/lookup_catalog, so an agent can pick it without opening the 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?

Explicitly gives the selecting condition: use it when you do NOT have a product ID, with a concrete example query. It does not name the sibling tools or state when lookup_catalog would instead be appropriate, which is why it falls 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.