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

Even with readOnlyHint and idempotentHint already set, the description adds substantial behavior: documents lacking a filtered field are silently excluded, pagination semantics (limit, offset, total, hasMore), result shape ({name, uuid}), and follow-up tools (uuid-resolve, compendium-browse). It also discloses the module version requirement. No contradictions with annotations.

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 long but tightly organized into CRITICAL DATA FORMATS, SEMANTICS, RESULTS, and EXAMPLES, with the core purpose front-loaded. Every section supplies necessary operational detail rather than padding, and the examples concretely demonstrate valid filter shapes.

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 13-parameter filter tool with no output schema, the description covers what is needed to call it correctly: filter semantics, edge cases, pagination behavior, return shape, and follow-up resolution. The annotations already cover the safety profile, and the description fills the remaining operational gaps completely.

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?

Although the schema has 100% parameter coverage, the description adds critical meaning beyond it: the exact valid CR set including the '1/4' -> 0.25 conversion and rejection of 0.3, size short codes, level applying only to type 'character', and the exclusion of world-only filters. It also explains range inclusivity and AND/OR combination, which the schema alone does not fully convey.

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 states a specific verb ('Search COMPENDIUM packs'), a clear resource (actors), and the D&D 5e structured-filter scope. It explicitly distinguishes itself from actor-filter (world actors) and compendium-search (plain name lookup), so an agent can separate it from near-names without inspecting schemas.

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 explicit usage boundaries: dnd5e worlds only, compendium packs only, and names the alternatives for other cases ('Compendium counterpart of actor-filter', 'for a plain name lookup use compendium-search'). It also states the semantic model (AND/OR, ranges, limits) that governs correct use.

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