ism_coverage_gaps

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

Annotations already indicate readOnlyHint=true. The description adds: never writes, reads `.ism-coverage.toml`, walks up from cwd, can run `ism_applicable` if `work` supplied, intersects results, and ranks by relevance score. It also describes ordering: uncurated > partial > deferred. This exceeds annotation-provided info and does not contradict.

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?

The description is concise and front-loaded: the first sentence gives the core purpose and a safety note ('Never writes'). The second paragraph adds necessary detail without redundancy. Every sentence earns its place.

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 an output schema present and good annotations, the description covers the tool's purpose, behavior, two modes, and ordering. It does not mention error cases or prerequisites (e.g., existence of manifest), but for a tool with this complexity, it is quite 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 coverage is 0%. The description explains `work` (triggers intersection with `ism_applicable` results for relevance) and `project_path` (defaults to cwd walk-up). `limit` is not described, only its default (50). Two out of three parameters get meaningful explanation, compensating for lack of schema description.

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 clearly states it returns outstanding in-scope controls (uncurated, partial, deferred). It distinguishes itself from the sibling `ism_coverage_read` by explaining the complementarity: 'read reports what is curated, gaps reports what is missing.' The verb 'return' and resource 'in-scope controls' are specific.

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 explains when to use it (to get gaps) and what it does (reads manifest, never writes). It contrasts with `ism_coverage_read` but does not explicitly compare with other siblings like `ism_coverage_impact` or `ism_get`. However, it provides clear context on two modes (with and without `work`) and mentions walking up from cwd.

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