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

Beyond the annotations (readOnlyHint=true, idempotentHint=true), the description discloses key behavioral traits: returns paginated {id, name} entries, filters combine with AND/OR, ranges are inclusive, actors lacking a filtered field are silently excluded, and pagination uses limit/offset with total/hasMore. It also details critical value constraints (CR is a number from an exact set, sizes are short codes, creatureType only SRD types) and that compendiums are not searched. This is substantial behavioral context that annotations do not provide.

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 well-structured and front-loaded: a one-sentence purpose, then usage examples, then critical data formats, then pagination details. Every sentence adds value; there is no filler or redundancy. Despite its length, it is concise relative to the complexity of 15 parameters and nested objects, and it is easy to scan due to clear section headers (CRITICAL DATA FORMATS, EXAMPLES).

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 (15 optional parameters, nested ranges, pagination) and the absence of an output schema, the description is remarkably complete. It explains filter combination, value constraints, edge cases (silent exclusion of actors lacking fields), pagination behavior, and directs the agent to actor-get for full stats. It also distinguishes from sibling tools. The only minor gap is behavior when no filters are provided, but the explicit note to use actor-list for unfiltered retrieval covers that context.

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 covers 100% of parameters with basic descriptions, the tool description adds critical semantic meaning: it explains that CR values must be from the exact set (rejecting '1/4' and '0.7'), sizes use short codes ('small' rejected), creatureType only accepts the 14 SRD base types (subtypes like 'demon' map to 'fiend'), ranges are inclusive, and missing fields are silently excluded. It also clarifies AND/OR semantics across filters. This goes far beyond the schema's per-field descriptions.

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 verb+resource: 'Search WORLD actors with D&D 5e structured filters (dnd5e worlds only).' It explicitly distinguishes from actor-list (unfiltered) and dnd5e-compendium-filter-actors (compendiums), so the agent knows exactly what this tool does and what it is not. The examples ('undead with CR 1-5', 'PCs in the party') further ground the purpose.

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 gives explicit usage guidance: 'Use for ...' with concrete examples, and clearly states when NOT to use it: 'For every actor unfiltered use actor-list; compendiums are NOT searched (use dnd5e-compendium-filter-actors).' It names the alternative tools and the conditions that select them, leaving no ambiguity.

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