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 genuinely new behaviour — no similarity cutoff, the list is always `limit` long, far matches appear when nothing is named in the library, and the no-query mode returns a large payload. The one gap is that it doesn't say how aliases/definitions affect matching beyond the names returned, but the risk profile is fully legible.

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 verb and the consumers, then the query mode, then the no-query mode — a logical order with no filler. It is dense with parentheticals and semicolons, which slightly slows parsing, but every clause carries information an agent needs.

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 burden and does so: it names `matches`, the per-match fields (kind, slug, English and Korean name, page url), the ordering, and the degenerate case where matches are semantically distant. For a three-parameter lookup tool, nothing an agent needs to call it or interpret the response is missing.

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 baseline would be 3, but the description goes beyond the schema by explaining that `limit` is always filled regardless of relevance, that matches are ordered nearest first, and that `kind` restricts to a single category with the result shape per match. The illustrative example ('cert ran out' → certificate-expiry) also clarifies what `query` expects, which the schema's 'A few words naming what you are looking for' does not.

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 — 'Resolves words to vocabulary slugs' — and immediately scopes it to the filters of search_incidents, list_incidents and get_topic, which tells an agent exactly where the output is consumed. It also covers the second mode (no `query` returns the full vocabulary), so both behaviours of the tool are named rather than implied.

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?

Gives explicit routing rules: prefer `query` because the unfiltered answer is large, read the returned names before using a slug, and when none fits, use search_incidents instead of filtering. That is a when-to-use, a when-not-to-use, and a named alternative, all in one paragraph.

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