规划工作流

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

The description explicitly states that planning will not modify the project, which aligns with and reinforces the annotations (readOnlyHint=true, destructiveHint=false). It adds concrete behavioral detail beyond the annotations by specifying what the validation covers: capability parameters, versions, risks, and side effects. This is consistent with the annotations and provides meaningful context about the tool's scope of analysis.

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 a single efficient sentence with two clauses, no filler, and the most important behavioral fact (no modification) is front-loaded at the end for emphasis. It earns every word. It could arguably add a bit more detail without becoming verbose, but as written it is appropriately compact.

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 a read-only planner with annotations already covering safety, the description conveys the core purpose adequately. However, it lacks several useful pieces of context: there is no output schema to explain the return value, no guidance on how to assemble the steps array, and no explicit statement of how this planning step relates to cocos_workflow_execute. The absence of parameter guidance and output semantics leaves notable 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 description coverage is 0%, yet the description adds no parameter guidance. It does not explain projectId or how to construct the steps array, nor the meaning of fields like expectedRevision, runtimeInstanceId, or instanceId within each step. The description only loosely references 'capability parameters.' Since the schema does not document these fields either and the description fails to compensate, an agent is left guessing at the structure of a non-trivial nested steps object.

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 states a specific action — batch-validating capability parameters, versions, risks, and side effects — and pairs it with the explicit scope 'planning will not modify the project.' This is clear and useful. It partially distinguishes the tool from the sibling cocos_workflow_execute by the non-modification statement, though it doesn't name the sibling. The verb 'validate' is slightly different from the name's 'plan,' which creates minor ambiguity about whether the tool produces a plan or only validates inputs.

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 'planning will not modify the project' clause implies this is a safe pre-execution step, hinting that it should be used before cocos_workflow_execute or other mutating tools. However, it never names an alternative tool or states explicit when-to-use/when-not-to-use conditions. The guidance is implied rather than stated, leaving the agent to infer that this is a dry-run/validation phase before actual execution.

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