governance_apply

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

With no annotations at all, the description carries the full burden and does meaningful work: it discloses the precondition ('Refuses a plan with active jobs'), the verification behavior ('Reads the result back'), and the two-mode execution ('Requires confirm:true; without it only what would run is returned'). It does not address permissions, or that delete-plan items are irreversible — a notable omission for a mutating 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?

Four short sentences with no filler, front-loaded with the action and the accepted item format before the operational caveats. The telegraphic phrasing is dense but unambiguous for a machine reader.

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 an unannotated mutation tool with no output schema, the description covers input grammar, precondition, dry-run gating, and that the result is read back. What remains unstated is the return payload's shape and the irreversibility/side effects of the delete-plan variant.

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 only 50% — the required 'item' parameter has no schema description — and the description fully compensates by spelling out the enumerable value grammar, which is the single most call-blocking piece of information here. It also restates and clarifies the confirm gate's semantics beyond the schema's wording.

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 ('Applies') and a specific resource ('ONE recommendation from governance_report'), then enumerates the exact accepted item grammar ('disable-plan:<id>', 'delete-plan:<id>', 'disable-task:<id>'). An agent knows precisely what this does and what input shape it consumes, distinct from the raw plan-mutation siblings.

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?

Clear usage context: the item must come from governance_report, and exactly one recommendation is applied per call (implying iteration for multiple items). It falls short of naming alternatives or exclusions — nothing tells the agent whether to use delete_plan directly instead of this governance-driven path.

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