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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description adds real value beyond that: default page size of 15, top-domains default, most-cited-first ordering, and domain filtering are all behavioral traits the annotations do not express.

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?

Three tight sentences with no filler, leading with the action and scope before adding the filter and the default behavior. The first sentence packs several clauses but remains readable and information-dense.

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 filtered, run-scoped list tool with an output schema already defined, the description covers ordering, defaults, and filtering adequately. It only omits how a run_id is obtained, which is reasonably inferred from the list_runs sibling.

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 75%, with limit/offset lacking descriptions but domain documented. The description restates "filter by domain" and "default returns 15," both already present in the schema, adding no format, range, or syntax detail. Baseline 3 applies.

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 (list) and resource (pages the engines cited), scoped to a single run, and even names the returned fields (times cited, engines, questions, domains) and sort order. It does not, however, contrast itself against siblings like get_results or get_receipts, which also surface run-derived evidence.

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?

"Use this to list... for one run" gives a clear context but offers no when-not guidance and names no alternative among the many siblings (get_results, get_receipts, get_proof). Usage is implied by the run-scoped framing rather than explicitly bounded.

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