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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds genuine non-obvious context: the data is mutable and written by the run itself, and it enumerates the content categories (progress, checkpoints, custom state), which tells the agent this is live state rather than a static record.

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 tight sentences with the payload description front-loaded before the API reference. The endpoint citation is slightly redundant but does aid traceability; no padding otherwise.

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 one required read-only param, no output schema, and existing annotations, the description is nearly sufficient. Naming the returned content categories compensates for the absent output schema, though it does not specify the metadata's shape or when it may be empty.

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?

Only one parameter (run_id) and schema description coverage is 100%, so the schema fully documents it. The description adds no format, sourcing or validation detail for run_id beyond the endpoint path. 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?

States a specific verb (Fetch) and resource (a run's metadata), and disambiguates the resource by listing what it contains: progress, checkpoints, custom state. This clearly separates it from sibling reads like trigger_get_run, trigger_get_run_span and trigger_get_run_trace.

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 — call it when you need the run's self-reported mutable state — but there is no explicit when/when-not guidance and no alternative named. It does not tell the agent how it relates to trigger_get_run for general run details.

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