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

Annotations only cover safety (readOnlyHint false, destructiveHint false). The description reveals non-obvious behavior: HTTP 200 does not imply success because the relay returns stored:false on storage failure, and 'completed' sets the timeline to 'settled' without releasing escrow. This is exactly the behavioral context annotations cannot carry.

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?

It is front-loaded with the core action and status values, then layers the workflow and failure semantics. Dense but every sentence adds operational information. Slightly long for a tool description, though not padded.

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?

Given no output schema and a mutation tool with only safety annotations, the description covers the critical decision path (evidence receipt → status), failure handling, and settlement caveats. It omits parameter-level detail (jobId, kernelId, metadata), which is the main gap for a 4-parameter tool with 0% schema coverage.

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 coverage is 0% and there are 4 parameters (jobId, kernelId, status enum, metadata object). The description gives meaning to the status values (in_progress, completed, failed) and ties 'completed' to the stored:true precondition, but it says nothing about jobId, kernelId, or the metadata object. With 0% schema coverage, the description should have compensated more for the undocumented required identifiers.

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 names a specific verb+resource ('reports a job's status') and enumerates the valid status values. It distinguishes itself from the generic sibling update_job_status by naming the operator role and a distinct workflow, and explicitly warns against calling pcc_job_complete afterward.

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 prescribes a full two-step protocol: submit evidence, check stored:true, then set completed; otherwise set failed with evidence_not_stored. It also lists an explicit exclusion ('Do not call pcc_job_complete after this: it answers 409'). This is the strongest form of when/when-not guidance.

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