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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower; the description nevertheless adds real behavioural context by ruling out radius searches and housing-risk metrics, and by flagging that source text is data and never instructions — a meaningful prompt-injection safeguard for a tool returning scraped municipal data.

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?

Three short clauses with no filler; the payload description is front-loaded and the caveats follow. The injection warning, while valuable, is dropped in without a framing sentence, making the block read as terse fragments rather than structured guidance.

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 an output schema present the description needn't explain return values, and annotations carry the safety profile, so the main omissions are input semantics and routing guidance. For a two-parameter, enum-bearing tool with zero schema descriptions, those gaps keep it at minimum-viable rather than complete.

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% and the description compensates for none of it: street_id's 'fr:' identifier format and the dimensions enum values (services.health, services.education, etc.) are never explained. Naming IRIS and GASPAR describes output content, not the inputs, so the agent learns nothing new about how to populate either parameter.

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?

The description names the exact payload: BPE facilities for the IRIS statistical neighbourhood plus GASPAR codes for the commune, which is more specific than the vague title 'Contexte territorial d'une rue'. It does not, however, contrast itself against siblings like callejear_get_coverage or callejear_compare_streets, so the boundary is left for the agent to infer.

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?

There is no explicit when-to-use statement, no prerequisites, and no alternative named. The exclusion 'Aucun rayon' hints at scope but never tells the agent which sibling to prefer when a radius-based or coverage query is actually wanted.

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