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

Goes well beyond the annotations by disclosing the AI-plus-rule-fallback extraction, deterministic ranking, return shape (criteria/understood, 6–12 models with 2–3 factual reasons, all-in budget estimate, relaxed criteria when empty, warnings with guide links), and a hard rate limit of 20 descriptions per day.

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-loads the input instruction, then the processing, return payload, a concrete example, the relaunch path, and the rate limit. Dense but every clause carries information; slightly long, yet no filler.

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 carries the return-value burden and does so fully: it enumerates criteria, understood, model count, reasons, budget estimate, relaxed criteria, and warnings. Rate limits and the relaunch mechanism are also covered, leaving nothing an agent needs to call it correctly.

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%, so the baseline is 3, but the description adds real meaning: criteria is the no-AI relaunch path (pass back a modified criteria object) and description is the natural-language project capped at 600 characters. This clarifies intent beyond the field names.

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 mechanism: takes a one-sentence natural-language project description, extracts criteria via AI with rule fallback, and deterministically ranks the 553-model catalogue. This clearly separates it from search_chalets or find_chalets_from_photo, though it never names those siblings 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?

It prescribes the input format (a French sentence covering terrain, surface, budget, usage, deadline, assembly, region) and explains how to relaunch without AI via a modified criteria object, so usage is implied. But it never states when to prefer this over search_chalets or find_chalets_from_photo, and no exclusions are given.

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