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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description still adds substantial behavior: the bridge module version gate (8.11.0+), that documents lacking a filtered field are excluded, that results carry level (null when absent), and that output is sorted by level then name. The response envelope (total, hasMore, {name, uuid}) is disclosed even though there is no output schema.

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 core purpose is front-loaded in the first sentence, followed by clearly labeled sections for data formats, filter semantics, response shape, and a compact worked example. No filler sentences; each line contributes a rule or a pointer the agent would otherwise have to guess.

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 an 11-parameter, nested-object filter tool with no output schema, the description supplies the missing pieces: result envelope, result fields, sort order, null-level behavior, and the version prerequisite. Pagination is handled by the schema's limit/offset, and hasMore is described, so nothing essential is left unstated.

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 the baseline is 3, but the description adds real semantics the schema cannot express: cross-filter AND, in-array OR, inclusive range bounds with min = max for exact match, and exclusion of documents missing a filtered field. One flaw: the blanket 'values inside one array with OR' conflicts with the traits parameter, which the schema explicitly documents as ALL-OF, so an agent could mis-predict trait filtering.

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 ('Search COMPENDIUM packs for actors'), scopes it to 'pf2e worlds only', and enumerates the structured facets (level, traits, rarity, size, HP, AC) that make it distinct from keyword search. It does not explicitly contrast itself with the closest siblings, compendium-search and pf2e-compendium-filter-items, or with actor-filter (world actors), leaving that differentiation implicit in the 'COMPENDIUM' emphasis.

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?

Usage context is implied through 'bestiary browsing' and the COMPENDIUM/pf2e-worlds scoping, and the description does route the agent to follow-ups ('uuid-resolve, or compendium-browse with ids to batch-load'). However, it never says when to prefer this over compendium-search, actor-filter, or the dnd5e sibling, and gives no explicit exclusions.

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