job.recover

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is well covered. The description adds only that risk is 'read' (redundant with readOnlyHint), maturity L3, and that per-request argument checks/session policy still apply. The per-request/session constraint is a small additional operational behavior, but the core recovery behavior (what happens to the target job) is not disclosed.

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 voice is short, but 'PartMe', 'Harness command', and 'Requirements: ' phrases add little value. It is concise but at cost of omitting the critical semantic. Just because it says nothing doesn't make it well structured.

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 job-lifecycle command with six sibling job tools, this description is severely under-referential. It doesn't explain what 'recover' does in the Blender Harness, how it relates to job_resume/job_cancel, or what the output schema implies. Even with an output schema, the purpose gap makes the entire operational context incomplete.

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?

Description doesn't add any meaning to the parameters beyond the input schema. Schema coverage is 60%, and the description compensates with no parameter information. jobId is required but never explained, and the harness metadata parameters (_requestId, _authorization, _transactionId) are only documented at schema level. The description fails to leverage its text where the schema is thin.

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 only identifies the tool as 'PartMe Blender Harness command job.recover' without stating what the command does. It does not name a behavior or resource, and the title 'job.recover' is essentially restated. The agent cannot distinguish this from sibling job_resume because no operation semantics are explained.

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?

There is no guidance about when a user/agent should call recover as opposed to job_resume, job_cancel, or job_status. The description mentions requirements ('per-request checks, session policy still apply') but gives no use-case context, prerequisites, or exclusions.

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