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

With no annotations provided, the description carries the full behavioral burden and does so well. It discloses ordering, omission of hooks, pagination semantics, the exact error case (422 invalid_cursor), cost ('Free'), and API shape equivalence, giving the agent a strong model of what the tool does before invocation.

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 dense but not bloated: every sentence contributes operational detail—scope, ordering, pagination, errors, follow-up actions, and cost. Information is front-loaded, starting with what the tool returns and how it is ordered.

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 paginated list tool with an output schema present, this description is complete: it explains the exact response envelope, pagination flow, error behavior, and next steps. The only minor omission is auth details around api_key, but this does not meaningfully hinder correct invocation.

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 only 33%, but the description compensates for the two most behaviorally important parameters: it explains limit bounds and default, and it gives cursor exact semantics (pass back next_cursor, null on last page). The api_key parameter remains unexplained, though its auth purpose is largely inferable from the sibling tool family.

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 clearly identifies the resource ('your research runs'), the ordering ('newest first'), and a key scoping detail ('without their hooks'), which differentiates it from related tools such as get_run, export_run, and find_hooks. The purpose is immediately understandable without needing to open the schema.

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 concrete operational guidance: how to paginate by passing next_cursor back as cursor, and which sibling tools to use next (get_run or export_run). It does not explicitly state when to avoid list_runs in favor of another listing tool, but the pagination and workflow context are clear enough for an agent to select it correctly.

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