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 genuinely useful context beyond that: the metadata is 'mutable' and is what the run 'has written about itself', telling the agent this is run-emitted state rather than static configuration. It does not cover return shape or pagination, keeping it short of a 5.

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 compact sentences, front-loaded with the resource and payload description, with the API path placed last as a verification aid. No filler or redundancy.

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?

For a single-required-param read tool with no output schema, the description adequately conveys what is retrieved (progress, checkpoints, custom state). It could say slightly more about expected return shape, but the annotations and schema cover the rest.

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?

There is a single parameter with 100% schema description coverage ('The run's id.'), so the schema already carries the semantics. The description adds no format, sourcing, or constraint detail beyond the schema, making the baseline 3 appropriate.

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+resource ('Fetch the mutable metadata a run has written about itself') and enumerates the metadata kind (progress, checkpoints, custom state), which distinguishes it from generic run retrieval. However, it never names or contrasts with the adjacent sibling trigger_get_run, so the agent must infer the boundary between run metadata and run details.

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 only implied: an agent can infer that this is the tool for reading self-reported run state, but there is no explicit when-to-use, when-not-to-use, or named alternative (e.g. trigger_get_run for full run details) to route between the two.

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