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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description goes beyond them usefully by describing the shape of the returned data and by flagging a non-obvious trap: 'sessions' contains every session of the run's role on the mission, so the agent must use runSessionId for this run's own log and cost. That is genuine disambiguation an annotation cannot carry.

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, zero filler, with the return payload front-loaded before the session-id caveat. The second sentence is somewhat dense ('sessions lists every session of the run's role on the mission; runSessionId names this run's own') and requires careful parsing, keeping it just short of ideal.

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?

With no output schema, the description must carry the return-value burden, and it does: it names the run record, the metric series, and the session summary fields (role, outcome, cost, sessionId), plus the session-vs-runSessionId distinction. Error or missing-run behavior is not covered, but for a read-only getter that is a minor gap.

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%, so the single sandboxId parameter is already documented as the run's sandbox id sourced from list_agent_runs. The description adds no format or syntax detail beyond what the schema provides, so the baseline of 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 (Fetch) and resource (one agent run) and enumerates the payload it returns: run record, CPU/mem/disk metric series, and session summaries. It implicitly distinguishes itself from list_agent_runs, get_agent_run_logs, and watch_agent_run by describing detail retrieval rather than listing, logging, or streaming, but it never names a sibling explicitly.

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?

Usage is implied rather than stated: the id comes from list_agent_runs (noted in the schema, not the description), and the tool is obviously the detail-fetcher for a known run. The description does supply one practical routing hint (read the log and cost from runSessionId rather than any other session), but there is no explicit when-to-use/when-not guidance or named alternative such as get_agent_run_logs.

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