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

Annotations already mark the operation read-only and idempotent. The description adds meaningful context: jobs are durable, and failed or interrupted mutations will not be automatically replayed. This tells the agent to expect persistence and manual inspection rather than automatic retries.

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 short sentences, front-loaded with the main purpose and followed by a useful caveat. Every clause earns its place and there is no redundant restating of the tool name.

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 read-only tool with only two optional parameters this is minimally adequate, but with no output schema the description does not explain the return shape, job statuses, or how limit/jobId shape the result. The failure caveat is organizationally relevant but does not fill those gaps.

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?

Schema description coverage is 0% and the description mentions neither jobId nor limit, so it does not compensate for the schema gap. The schema's field names and constraints carry the only semantics, and the description adds no guidance on how to filter or page.

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 uses a specific verb and resource: 'Read durable processing/result jobs' and scopes it to the authorized workspace. It is clear, but it does not explicitly distinguish this from sibling read_* tools or say what qualifies as a 'job'.

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 by the read semantics and the caveat that failed/interrupted mutations are not automatically replayed, which hints that this tool is how you inspect job outcomes. There is no explicit when-to-use statement, alternative routing, or exclusions.

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