cmake_run_test

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

Annotations already declare destructive/openWorld/non-idempotent, so the safety profile is covered. The description adds real value beyond that: environment inheritance, cwd default, zero-exit-as-success convention, and the pass-through to process_get for output. It stops short of explaining side effects on the target or cleanup behavior.

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?

Five terse sentences, each earning its place, with the core verb and the key differentiator front-loaded. No redundancy.

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?

Output schema exists so return values need not be explained, and annotations cover safety, but the description leaves the executable and timeout parameters undocumented despite 0% schema coverage. Adequate for routing but incomplete for correct invocation of all four parameters.

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% across 4 parameters, so the description must compensate. It only clarifies cwd (defaults to project/) and the literal nature of arguments; executable and the ProcessTimeout idle/total fields are left fully undocumented by both schema and 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?

States a specific verb ('Run') and resource ('one project/storage test executable') and immediately scopes it with 'directly with literal command-line arguments.' It also distinguishes itself from the sibling cmake_test by explicitly excluding 'profiles, CTest properties, or case reports.' An agent can tell the two apart without opening a schema.

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 exclusions ('No profiles, CTest properties, or case reports are used') imply the contrast with cmake_test without naming it, and the workflow is spelled out ('Read output through process_get with the returned process_id'). Clear context for using it, but no explicit when-not or named alternative.

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