aiworkhub_quality_gate_ratchet

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

The description restates readOnlyHint=true ('READ-ONLY') without adding context, which earns no credit. It does not disclose whether the 'ratchet' compares against persisted baseline state, what 'overflow' means, or what the report contains beyond what the output schema presumably covers.

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?

One short sentence with no filler, but the space is spent on a redundant 'READ-ONLY' prefix rather than on the concept the agent actually needs. Front-loading is technically correct but the payload is thin.

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 needn't be described, but for a tool whose entire premise is a 'ratchet' baseline comparison over caller-supplied violations, the description leaves the core semantic model and the parameter contract unexplained.

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 the single optional 'violations' parameter (array of untyped objects), so the description must compensate, and it does not. It never explains what a violation record should contain or what 'quality identity' means in that payload.

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 verb 'report' is present, but the resources 'quality identities' and 'no-net-growth overflow' are undefined internal jargon that an agent cannot map to a concrete operation. Nothing distinguishes it from siblings like aiworkhub_quality_run_checks, aiworkhub_eval_artifact_gate, or aiworkhub_quality_profile.

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?

No indication of when this tool should be called, what precedes it (e.g., a check run producing violations), or which sibling to use instead. The only signal is the 'READ-ONLY' prefix, which merely implies it is safe, not when it is appropriate.

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