apply_plan

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

No annotations are provided, so the description carries the full burden. It discloses scope of modification (configs only, never train.py), provenance recording, and error envelope behavior. It does not mention whether the operation is reversible or what happens on success, but it provides significant behavioral context.

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?

Three sentences, each serving a distinct purpose: what the tool does (modify cq.yaml.configs), side effect (provenance recording), and return behavior (error envelope). No wasted words, front-loaded with purpose.

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?

The description covers key aspects: scope, provenance, error handling. However, it does not describe success return value or behavior, which would be helpful given no output schema. It also lacks differentiation from sibling apply_planset. Still, it's largely complete for a tool with this complexity.

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 67% (plan and plan_file have descriptions; path has none). The description adds no extra semantics for path or plan_file beyond the schema. For plan, the schema already includes a detailed example; the description's mention of error envelope adds slight context. Overall, baseline 3 is appropriate.

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 explicitly states the tool applies an ExperimentPlan to a project and specifies it modifies only cq.yaml.configs, never train.py. This clearly differentiates it from siblings like apply_planset or run_experiment.

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 mentions provenance recording and error returns but does not provide explicit when-to-use or when-not-to-use guidance relative to siblings like apply_planset. Context is implied but not directed.

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