aiworkhub_manager_skill_retirement_report

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

Beyond the readOnlyHint annotation, it clarifies that verdicts are recommendations, retirement is manager-gated, it 'never writes,' and it declines to compute rates against a zero denominator (reporting both counts instead). That is meaningful context the annotation does not 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?

Front-loaded with the core purpose, then behavior, then the mode split. Dense but each sentence carries information; the denominator sentence is verbose but discloses real behavior.

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?

An output schema exists so return values need not be explained, and the mode behavior is covered. However, with 0% schema coverage the undocumented `min_anchors` parameter leaves a real gap for an agent deciding how to call it.

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%, so the description must carry parameter meaning. It explains `full` well (summary folding vs unchanged anchor lists) but says nothing about `min_anchors`, leaving one of two params documented nowhere.

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?

'measure every stored skill against its own failure class' plus 'Reports, per skill, whether it is injectable at all' gives a specific verb and resource. It is reasonably distinguishable from siblings like skill_usage or skill_evidence_sweep by the retirement/failure-class framing, though the phrasing is jargon-heavy.

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?

The description implies this is the retirement-assessment read ('Verdicts are recommendations; retirement stays manager-gated') but never states when to call it versus skill_usage, skill_evidence_sweep, or skill_activate. Usage is inferable rather than explicit.

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