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

With no annotations, the description carries the full burden and does most of it: it discloses cost/quota ('free and without quota'), the confidence scale (0-1), normalisation, the per-country supported flag, and the meaning of ambiguous=true. The gaps are what happens on no match or invalid input, and the exact response shape, which it only gestures at.

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-loaded with the key distinction and trigger, and every sentence carries information. It is tightly compressed to the point of being telegraphic in places, which slightly hurts scanability but wastes no words.

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?

For a two-parameter classification tool with no annotations and no output schema, the description covers purpose, when to call, ambiguity handling, key return fields and the follow-up call. Only failure/no-match behavior is left implicit.

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%, including the hint enum description ('it only reorders the candidates'), so the schema already does the parameter work. The description's only added input insight is that bare digits are what trigger ambiguity; it says nothing extra about hint or the 200-character text limit.

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: classify a piece of text as a cadastral reference, coordinate pair or place name, per candidate country. It names what the output carries (confidence, normalised form, supported flag), so an agent can distinguish it from get_parcel without opening either schema.

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?

Explicit triggers: use it when get_parcel answers CNV_AMBIGUOUS, or to find the country of an unknown reference. It also closes the loop on the ambiguous=true branch by instructing the agent to pick a candidate and pass it as country to get_parcel.

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