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

The description adds substantial behavior beyond the annotations: lifecycle calls cost 0 credits while queries are metered with reservation and refunds, query is async and returns 202, matching is literal and deterministic with no stemming or fuzzy inference, and coverage is returned even for members with zero matches so partial crawls are not misread. It also discloses privacy handling and the API key requirement. No contradiction with annotations.

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 long but dense and front-loaded. The first sentence states the core purpose and differentiation, the action list embeds lifecycle order, and separate sentences address matching behavior, credit costs, and privacy. Every sentence contributes useful decision or invocation signal; there is 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?

Despite having no output schema, the description covers the essential return shape (items plus coverage), the asynchronous query flow via query_status, the credit reservation model, and the required API key. Combined with the highly detailed input schema and action enum, an agent has enough context to select, invoke, and interpret this multi-action tool 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 coverage is 100% and the schema already documents each parameter in detail, so the baseline is 3. The description adds meaningful cross-parameter context: estimate_cost is local and sizes max_credits, add_members upserts on external_id, query_results carries items plus coverage, and matching semantics clarify keywords/date constraints. It does not individually elaborate every parameter, but the schema already carries that weight.

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 concrete question and explicitly positions the tool as 'the opposite of open social listening'. It states the resource (a cohort of up to 10,000 public handles), the action (keyword mention search), and the result (matching posts plus coverage), making it easy to distinguish from open-listening siblings.

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 clearly tells an agent when to use this tool: when the target set is a known panel of specific identities rather than the open social graph. It also provides a helpful lifecycle order for the actions. However, it does not explicitly name sibling alternatives like socialcrawl_discover or socialcrawl_monitors, so the exclusion guidance is implied rather than direct.

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