apply_plan

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

With no annotations, the description fully bears transparency. It discloses that the tool modifies only cq.yaml.configs, records provenance under .pcq/plans/, and returns rejected envelopes with specific reasons on invalid input. This covers core behavioral traits, though it omits information about idempotency or whether the operation is reversible.

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 extremely concise—two sentences covering action, scope, provenance, and error behavior. Every sentence adds value without redundancy or extraneous detail.

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?

Given the tool's complexity (nested object, no output schema), the description covers action and error responses but lacks success output details, prerequisites (e.g., project must exist), and integration with sibling tools like init_experiment. It is minimally complete but leaves gaps for an agent.

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 67% (path parameter lacks description). The tool description does not clarify the 'path' parameter's purpose or format, nor does it add semantic information beyond the schema's detailed 'plan' parameter description. The description's mention of error responses does not compensate for missing parameter guidance.

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 the tool applies an ExperimentPlan to a project, specifies the scope (modifies cq.yaml.configs only, never train.py), and distinguishes the action from generic 'plan' operations. The verb 'apply' combined with the resource 'ExperimentPlan' and the boundary 'never train.py' provides precise purpose, though it doesn't explicitly differentiate from the sibling 'apply_planset'.

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 offers no explicit guidance on when to use this tool versus alternatives like apply_planset, run_experiment, or validate_project. It implies usage for single plan application but lacks exclusion criteria or context about prerequisites (e.g., project must be initialized).

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