read_run_status

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

With no annotations, the description must disclose behavioral traits itself. It does so thoroughly: explains the polling pattern, expected status transition to 'succeeded', availability of result endpoints, and failure handling with data.error. This goes beyond superficial 'get status' and gives the agent a clear mental model of the tool's behavior.

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?

The description is concise and front-loaded with the core purpose. It uses multiple sentences to cover the polling lifecycle, success/failure states, and endpoint availability. While the final sentence slightly reiterates the earlier polling advice, each sentence contributes meaningful guidance, keeping the overall structure clean and scannable.

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?

The description is contextually complete for this simple status-polling tool. It explains the workflow (post-start_run polling, result endpoint dependency), handles both success and failure outcomes, and references specific sibling tools. Given the single parameter and existing output schema, the description provides all necessary operational context without over-explaining.

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 provides 100% coverage for the single 'token' parameter, clearly stating it is returned by start_run. The description does not add additional parameter-level semantics, so the baseline score of 3 is appropriate, as no further compensation is needed.

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 clearly states the tool returns the run's current status with a specific verb ('Returns'). It differentiates from sibling tools by explicitly describing the polling workflow and its relationship to result endpoints (read_result_summary, etc.), which are not called until this tool indicates success. The purpose is unambiguous and contextually anchored to start_run.

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?

It provides explicit when-to-use guidance: poll after start_run until succeeded, and always confirm completion before calling result endpoints. It also identifies the alternative behavior on failure (data.error). This directly tells the agent when to invoke this tool relative to the run lifecycle and sibling read tools.

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