find_slots

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the returned fields are enumerated, practitioner-level status is described, and it discloses latency (10-60 s) plus the underlying rate limit (~3 req/s to Doctolib) — rare and valuable operational context.

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 front-loaded sentences; the core capability leads and the return shape and latency follow. Efficient, though the return-field enumeration is a little list-heavy.

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 commendably explains the return payload and per-practitioner status, and it warns about runtime. But for a 10-parameter aggregation tool at 0% schema coverage, the missing parameter semantics leave the definition under-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% across 10 parameters, so the description carries the full burden. It only loosely maps to speciality, location and days ('sur N jours'); it never explains lat/lng vs city precedence, radius_km, sector_1_only, new_patients_only, max_slots_returned, or include_telehealth_kiosks.

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 and resource ('TOUS les créneaux libres d'une spécialité') with clear scope: around a location, over N days, in one call. It is distinguishable from aggregation-free siblings, but never names the competing tools (search_availabilities, get_availabilities) to sharpen the distinction.

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 'en un appel' implies this aggregates what scattered siblings do, but there is no explicit when-to-use, when-not-to-use, or named alternative. The agent is left to infer that this replaces search_availabilities/get_availabilities from the sibling list alone.

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