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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: documents lacking a filtered field are silently excluded, filters combine with AND/OR semantics, results are sorted by level then name, and the response includes total and hasMore. It also discloses the bridge module version requirement (8.11.0+), which is useful operational context. It doesn't describe pagination edge cases or error behavior, but the disclosed semantics are substantial.

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 dense but well-organized with clear section headers (CRITICAL DATA FORMATS, SEMANTICS, EXAMPLES). It front-loads the core purpose and scope before diving into details. The examples are compact and illustrative. It is longer than strictly necessary, but every section earns its place given the tool's 11 parameters and complex filter semantics; a small deduction for the length and some redundancy between the SEMANTICS section and the schema descriptions.

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 complex filter tool with 11 parameters, nested range objects, and no output schema, the description covers the essential semantics: filter combination logic, range inclusivity, silent exclusion of missing fields, pagination limits, result shape ({name, uuid}), and follow-up tools. It lacks explicit return field details beyond name/uuid/level and doesn't document error conditions, but the provided context is sufficient for an agent to construct valid queries and interpret results 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 description coverage is 100%, so the schema already documents every parameter. The description adds meaning beyond the schema by explaining the critical data formats: level is an integer range with negative bounds valid, traits are ALL-OF lowercase slugs, rarity follows the PF2e ladder, and ranges are inclusive with min=max for exact. It also clarifies that values inside one array use OR while filters combine with AND, which is not evident from the schema alone. This goes beyond the baseline 3 for full schema coverage.

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 specific verb ('Search') and resource ('COMPENDIUM packs for actors'), and immediately distinguishes itself from generic actor-filter by scoping to PF2e structured filters and pf2e worlds. It also names sibling tools (uuid-resolve, compendium-browse) for follow-up, making its role in the tool family clear.

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?

The description explicitly states when to use this tool ('pf2e worlds only'), what filters it supports, and how results should be followed up ('follow up with uuid-resolve, or compendium-browse with ids to batch-load'). It also contrasts with the sibling dnd5e-compendium-filter-actors by naming the PF2e-specific scope, giving an agent clear selection criteria.

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