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

Even with readOnlyHint and idempotentHint annotations present, the description adds meaningful behavioral detail: it lists the returned envelope fields, defines the terminal statuses, and describes the polling loop. It also clarifies the read-only scope and what `output` contains on success. There is no contradiction with annotations.

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?

Four compact sentences, front-loaded with the action and resource, with every sentence earning its place: source endpoint, return envelope, polling semantics, and read-only exclusion. 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 one-parameter, read-only poller with an output schema, the description covers invocation, expected response shape, terminal states, and success payload structure. Nothing essential for correct use is missing.

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?

The input schema already fully documents the single `jobId` parameter with the same meaning, and schema description coverage is 100%. The description restates that the job ID comes from the submit call, but adds no additional format, constraints, or edge-case semantics beyond the schema. Baseline 3 is 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?

The description opens with 'Fetch an Agent run,' naming the exact verb and resource, and ties it to `post_exa_agent_runs` by `jobId`. It explicitly frames the tool as read-only ('Reads a run only; it cannot start one'), distinguishing it from sibling submit tools like `post_exa_agent_runs.

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?

The description gives a clear usage pattern: fetch the run submitted by `post_exa_agent_runs`, then 'Repeat until `status` is `completed`, `failed` or `cancelled`'. It also states the when-not case, 'it cannot start one', which routes creation to the correct sibling. This is explicit and actionable.

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