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

Annotations already cover read-only/idempotent safety, but the description adds genuinely non-obvious behavior: actors lacking a filtered field are silently excluded (PCs have no CR, vehicles no abilities, root-level actors no folder), filters AND across fields but OR within an array, and the response carries total and hasMore. That silent-exclusion rule is exactly the kind of trap an agent would otherwise hit.

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 a CRITICAL DATA FORMATS block, then one concrete example. Given 15 nested parameters, every section carries information an agent needs; no 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?

Fifteen nested params, no output schema — yet the description compensates by declaring the return shape ({id, name} entries plus total/hasMore) and the field-availability exclusions. Nothing essential for a correct call 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%, so the baseline is 3, but the description adds real semantics the schema cannot express: CR must come from the exact set 0/0.125/.../30 with the 1/4->0.25 mapping and 0.7 rejected, ranges are inclusive with min=max for exact match, and a worked example showing combined filters with recursive folder. This meaningfully reduces malformed calls.

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 WORLD actors with D&D 5e structured filters'), gives the scope restriction (dnd5e worlds only) and the return shape ({id, name}, paginated), and explicitly names the two sibling tools it is not (actor-list, dnd5e-compendium-filter-actors). An agent can distinguish it from all 100+ siblings immediately.

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?

Explicit routing: use actor-list when unfiltered, dnd5e-compendium-filter-actors for compendium content, and this tool for filtered world searches. It also tells the caller to chain into actor-get for full stats, which is the key follow-up decision.

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