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

Annotations already declare readOnlyHint, idempotentHint and non-destructive, so the safety profile is covered. The description adds real operational context beyond that: the returned payload depends on run state (result when finished, status while running), which tells the agent this is a safe repeated-poll call. It does not describe failure/error behavior or any polling interval, which keeps it out of 5 territory.

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?

One sentence, front-loaded with the action and resource, with the state-dependent return tucked in as a subordinate clause. Nothing is wasted and nothing important is buried.

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 carries the burden of explaining return values and does so at a high level (result vs status). It omits what a finished-but-failed run returns and whether the result is inline or by reference, which are minor gaps for a one-parameter read tool.

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?

With a single parameter and 100% schema description coverage, the schema already documents run_id and its provenance (returned by run_tool, run_job or run_recipe). The description adds no additional meaning about the identifier, so the 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?

The description states a specific verb (fetch) and resource (a run) and clarifies the two things it can return: a result or a status. It is clearly distinct from the run-starting siblings (run_tool, run_recipe) though it never names them explicitly, so the reader must infer that this is the retrieval counterpart.

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?

'or its status while it is still running' implies the tool can be called at any point in a run's lifecycle, which hints at polling usage. However, it never states when to prefer this over get_recipe/get_usage or that it should be called repeatedly until completion, so the usage guidance remains implied rather than explicit.

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