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

Annotations declare readOnlyHint=false, so the agent knows this is a mutation; the description adds genuinely useful behavior beyond that — only host runners may call it, and submitting checks does not complete the job. It does not explain what is written, whether resubmission is idempotent, or how the runner credentials (submitHmac/runnerNonce/runnerToken) are used.

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 short and front-loads the host-runner constraint, but the telegraphic fragments ('Completion-loop:', 'No job_complete.') do not read as complete instructions and one clause is effectively unintelligible. Brevity is achieved here through omission rather than compression.

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 7-parameter mutation carrying signing/nonce/token fields, the description leaves the caller with no guidance on obtaining or supplying those credentials, and no explanation of the results payload shape. The output schema covers return values, but the input side is a substantial gap the description does not close.

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% across 7 parameters, including security-sensitive ones (submitHmac, runnerNonce, runnerToken) and structural ones (results, gitSha, treeHash) that are entirely undocumented. The only semantic hint is 'Do not invent results,' which tells the agent results must come from real execution but says nothing about field meaning, formats, or which of the two required params pair with which.

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 says 'Completion-loop: host runner only' but never states the actual operation — that it submits check results for a job. Only the schema (jobId + results array) reveals what the tool does, so an agent must open the schema to learn its purpose. The 'verify_task' exclusion does help separate it from one sibling.

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?

Explicit caller restriction ('host runner only'), two named invocation paths ('toolyour-check-run or control-plane-host.mjs'), and a clear exclusion ('Do not use for skill-loop verify_task jobs'). The 'No job_complete' clause is cryptic rather than clarifying, but the when/when-not framing is otherwise strong.

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