get_task_evidence

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

No annotations are provided, so the description must carry the behavioral burden. 'Retrieve' implies a read-only lookup and 'verified' hints that returned receipts/verdicts are authoritative, but the description does not state error behavior for unknown run_id/task_id, whether results are cached or live, or the payload shape. Useful content disclosure, but incomplete for a zero-annotation tool.

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?

A single front-loaded sentence with the resource and scope stated immediately. No filler, no restatement 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?

With no output schema and no annotations, the description does enough to convey the return content (executor receipts plus QA verdicts) but leaves the two required identifiers and failure modes undocumented. Adequate to attempt a call with inherited IDs, not complete.

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% for both parameters, so the description must compensate and does not. It mentions 'a specific task', loosely mapping to task_id, but never explains what run_id is, how the two identifiers relate, or what happens if they are mismatched.

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?

States a specific verb (Retrieve) and a concrete resource (verified executor receipts and QA verdicts) scoped to a specific task. The term 'evidence' is unpacked into two artifact types, so an agent knows what comes back. It does not explicitly contrast with siblings such as get_run or list_tasks, keeping it at 4 rather than 5.

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 statement of when to call this versus get_run, get_agent_status, or other task-level inspection tools, and no prerequisites or exclusions. At best the phrase 'for a specific task' implies it is called after a task has executed, which is inference rather than guidance.

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