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

Annotations already declare a safe idempotent read, but the description adds substantive behavior: AND across filters, OR within arrays, inclusive ranges, exclusion of documents lacking a filtered field, response shape (total/hasMore), a bridge version requirement, and that results are thin {name, uuid} objects needing uuid-resolve or compendium-browse to hydrate. That is well beyond the annotation bar.

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 purpose sentence, then scannable CRITICAL DATA FORMATS and EXAMPLES blocks, then a single runnable example. Every line carries a constraint or routing decision; nothing is filler.

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 tool with nested range objects, no output schema, and no required parameters, the description covers the risk areas: data formats, filter combination logic, field-exclusion behavior, pagination signals in the response, and the follow-up call needed to turn results into documents. Nothing an agent needs to call it correctly 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%, yet the description still adds meaning: it enumerates the exact valid CR set and shows the fraction conversion ('1/4' -> 0.25; 0.3 is rejected), spells out min = max for exact matching, and warns that creatureType has no subtypes ("demon" -> "fiend"). These are real constraints beyond what the schema text conveys.

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 (search), resource (compendium packs for actors), and differentiator (D&D 5e structured filters, dnd5e worlds only). It explicitly positions itself against two siblings, actor-filter and compendium-search, so the agent can distinguish it without opening any schema.

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 names both alternatives and the condition that selects them: actor-filter for world actors, compendium-search for plain name lookup. It also states the negative case (world-only filters such as folder, hasPlayerOwner, currentHp do not exist here), which prevents a whole class of failed calls.

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