compute.get_run

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

readOnlyHint=true already tells the agent this is a safe read, so the bar is lower. The description does add real context by disclosing that it refreshes from the executor, implying a live backend round-trip with possible latency or failure. It does not state what happens when the run is unknown or how fresh the data is with refresh disabled.

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?

A single well-formed sentence with the action front-loaded and no filler. It is efficient, though the terse phrasing leaves little room for the clarifying detail the tool actually needs.

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 usefully names the return payload (state, exit code, recent events). However, for a run-inspection tool in a dense sibling set it still omits error behavior for missing runs and the latency/freshness trade-off implied by refresh, leaving meaningful gaps.

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 0% for two parameters, so the description carries the full burden. It gestures at the refresh behavior with 'refreshing from the executor' but never explains what refresh=false returns (cached state?) or whether the call blocks, and run_id gets no explanation of format or source.

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?

Uses a specific verb (Fetch) plus a clear resource (a run) and enumerates the returned fields: state, exit code, recent events. An agent can distinguish it from list/wait tools. It stops short of naming how it differs from compute_get_run_progress or compute_get_logs, which are the closest siblings.

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?

There is no explicit when-to-use or when-not-to-use guidance and no mention of alternatives in a 29-tool family that includes compute_get_run_progress, compute_wait_run, compute_get_logs and compute_list_runs. The agent must infer from the nouns alone which retrieval tool to pick.

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