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

Annotations only declare readOnlyHint, so the description carries real weight here and delivers: transcript is readable for any run in the organisation (authorization scope), the transcript arrives one window at a time with tail-vs-sequence semantics, and it corrects a likely misreading by explaining turns_used counts sessions while tool_iterations counts actual tool calls.

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 with the purpose and the returned fields; every paragraph earns its place by covering a distinct behavior (outcome completeness, turns_used trap, transcript pagination). It is dense but somewhat long, and the pagination walk is partly duplicated from the schema descriptions.

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?

No output schema exists, so the description must, and does, enumerate the returned fields and the transcript windowing behavior. Combined with the readOnly annotation, an agent has everything needed to call this correctly and interpret results.

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 genuine meaning: it clarifies include_transcript inlines the transcript with assistant prose in payload_text, and spells out the walk pattern (start at since_sequence 0, pass back next_since_sequence while transcript_has_more_after is true). It also restates the default non-transcript behavior of transcript_limit, which is mostly redundant with the schema.

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 ('Fetch one dispatched AI agent run in full') and enumerates exactly what is returned: status, trigger context, timings, outcome summary, goal status, session id, tool_iterations. It explicitly contrasts with the sibling list aid by saying 'the run list clips it, this does not' and points to list_agent_runs for the run_id.

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?

Clear routing guidance: 'Identify the run by run_id from list_agent_runs', and it explains when to set include_transcript and how to walk a long transcript. It does not give explicit when-not-to-use conditions, but the context for choosing this over the list tool is well established.

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