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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, so safety is fully covered. The description adds meaningful behavioral details: the `type` filter is baked in, the default response is a compact summary, and `detail: 'full'` returns the full stat block inline. It does not contradict annotations and adds context beyond them, though it stops short of discussing pagination behavior or edge cases (which the schema covers).

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 description is four sentences, each earning its place: purpose, sibling contrast, default vs full detail, and pairing suggestion. It is front-loaded with the core function and uses no filler language. Structure is both concise and information-dense.

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?

Given the tool's complexity (search, filtering, pagination, detail levels), the description covers all essential aspects: what is searched, the baked-in filter, default vs full shape, and a recommended follow-up. The output schema exists, so return-value details are not the description's burden. No critical usage information is missing for an agent 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 all six parameters are already described. The description adds value by clarifying the `detail` parameter's effect, enumerating the fields included in a full stat block (attributes, defense, offense, AC, HP, actions, skills), and stating that `name` supports `^name$` for exact match. This goes beyond the schema's generic wording, justifying a score above baseline.

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 description opens with a precise definition of what the tool does: search authored monsters (characters with the `type: monster` marker) plus stock templates. It explicitly contrasts with the sibling `vault_search_characters`, which hides monsters by default, making the tool's purpose unmistakable and distinct from every sibling.

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 states this is 'the right tool for creature stat-block lookups' and explains why the sibling exists, directly addressing when to use this tool over `vault_search_characters`. It also suggests pairing with `vault_get_character` for full documents, giving actionable usage context. The guidance is explicit and includes alternatives.

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