professionnels_in_radius

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

Adds significant behavioral context beyond annotations: distance is haversine (great-circle), multi-sites appear multiple times without deduplication, limit applied before dedup, cache behavior for freshness parameter, data source (Ameli) with weekly updates, and legal reuse note. Annotations already indicate read-only and idempotent, but description enriches with operational details.

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?

Description is comprehensive but not overly verbose; it covers multiple aspects in a logical order. Could be slightly more concise by grouping related points, but given the complexity (8 parameters, exceptions), the length is justified. Front-loads main purpose and then details. No tautology.

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?

Given the tool's complexity (8 parameters, multiple filtering options, deduplication, freshness, output schema), the description covers all necessary context: geospatial precision, parameter semantics, dedup behavior, limit ordering, out-of-scope professionals, data source, update frequency, and legal citation. With an output schema present, return values are presumably documented elsewhere.

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 coverage is 100%, but description adds substantial meaning: clarifies that type_ps_codes has only 3 stored values ('1','2','5') and suggests using specialite_codes for targeted professions. For dedupe_by_ps, explains grouping logic and default behavior. For include_freshness, explains purpose and cache benefit. Parameter descriptions are already good, but description adds real-world usage context.

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?

Clearly states the tool searches for liberal healthcare professionals (libéraux conventionnés) within a geographic radius. Specifies the resource (professionnels de santé libéraux conventionnés) and action (recherche dans un rayon), distinguishing it from sibling tools like 'professionnels_rpps_in_radius' and 'etablissements_finess_in_radius' by focusing on Ameli data for conventionné professionals.

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?

Provides explicit guidelines: when to use specialite_codes over type_ps_codes, how dedupe_by_ps works, and that limit is applied before deduplication. Also explains out-of-scope cases (hospitaliers, salariés) and directs to alternative sources (Annuaire Santé ANS) for complete data, and mentions using external services for driving distance.

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