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

With no annotations present, the description carries the full burden of behavioral disclosure. It covers cost, read-only idempotency, concurrent start, per-engine error handling, and the output shape including 'model' and 'structured error per engine'. This is exceptional transparency for a paid, multi-engine tool.

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?

Two sentences, with the core action and output summary front-loaded. Every clause adds value: engines, scope, reported fields, concurrency, failure behavior, cost, and retry safety. No filler or repetition.

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 lacking an output schema, the description lists the returned fields (cited status, count, domains, model, error) and failure behavior, which is sufficient for an agent to interpret results. Cost and retry safety are included, and input constraints are fully covered by the schema. Complete for a paid read-only API call.

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 description coverage is 100% with detailed per-parameter info (e.g., domain normalization pattern, engine enum). The description adds context that target domains are the citation objects and prompt is sent verbatim, but does not materially expand on the schema. Baseline 3 is appropriate.

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: 'Sends one prompt to 1 to 4 search assistants' and reports citation info for 'target domains'. Names the four engines and the exact output fields, making the tool's function explicit. The multi-engine scope also distinguishes it from the sibling per-engine citation_tracker_check_perplexity.

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?

Does not explicitly name alternatives or give when-not-to-use conditions, but provides clear behavioral context: concurrent execution, failure isolation ('a failed engine returns `cited: null` and does not block the others'), and cost ('$0.75/call'). The 'safe to retry' note gives a practical guideline. Lacks a direct contrast with sibling tools, but the context is strong enough for a 4.

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