Character name match

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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so safety is covered. The description adds genuine behavior beyond that: it discloses that `matched_on` and `score` carry trust signal, that results are ranked, and that a threshold can yield an empty result set — enough for the agent to handle the no-match case. It does not discuss scoring methodology, tie-breaking, or how many candidates typically clear the default threshold, which a ranking tool would ideally address.

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?

The three-sentence preamble front-loads purpose then the failure condition then the decision guidance, and the Args block is scannable. Every sentence earns its place; only the trailing newline-separated docstring formatting is slightly verbose, but nothing is wasted.

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?

An output schema exists, so return shape needn't be documented, and the description still usefully previews `score` and `matched_on` as interpretation aids. For a 3-parameter read-only ranking tool the coverage is nearly complete; only scoring semantics and defaults are absent.

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 0%, so the description must carry the load, and it largely does: it explains `query` accepts a name in any script with CJK, kana and romaji examples, gives `top_k` a 1-20 range that the schema omits, and defines `threshold` as a 0-1 minimum whose effect is that nothing below it is returned. It does not state the defaults (5 / 0.45) or how the score is scaled, leaving a small gap.

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 first sentence states a specific verb and resource: rank characters by name similarity to a query. It is clearly distinguishable from an exact lookup, and the second sentence reinforces the fuzzy-matching nature by framing it as the fallback when a name is not in the table. It never names `character_lookup` explicitly, so sibling routing relies on inference.

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 gives a concrete triggering condition — a lookup failed because the name is absent — and a downstream action policy: use `score` and `matched_on` to decide whether to ask the user rather than guess. There is no explicit exclusion (e.g. 'do not use when you have an exact ID'), which keeps it a step below a 5.

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