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

With readOnly/idempotent/non-destructive covered by annotations, the description still earns credit for disclosing provenance and a reliability caveat: links come from a local manifest "sans garantie de disponibilité actuelle," and results are unranked residentially. That is real behavioral context beyond the annotations, though it omits anything about result shape or pagination.

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?

Two compact sentences, front-loaded with the core purpose and scope before the caveat. No filler, though the density of the second clause is a minor readability cost.

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?

An output schema exists, so return values need not be described. However, for a 4-parameter tool with zero schema descriptions, the description leaves limit and cursor semantics entirely unexplained, so it is not fully complete despite the useful provenance note.

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 0% across 4 parameters, so the description must carry the full burden. It only clarifies that city_id is an INSEE code; query, limit (max 20), and cursor (pagination) receive no explanation, leaving the majority of parameters undocumented.

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 textuelle") and resource (streets) scoped to a single commune, and adds the negative constraint "pas de classement résidentiel." This distinguishes it from the sibling callejear_search_communes by resource, though it never names that sibling explicitly.

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 phrase "dans une seule commune identifiée par son code INSEE" implies the tool is limited to one municipality at a time, which is useful scoping, but there is no explicit when-to-use vs. when-not guidance or mention of the sibling alternatives (compare_streets, get_street_context, search_communes).

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