plan

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

With no annotations, the description fully discloses that the tool is read-only, never mutates the tree, and uses the 'architect' persona. It also describes the purpose of key parameters. However, it does not mention the behavior of the output, such as the format of the returned plan, though an output schema exists.

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 relatively concise with 3 sentences, and the first sentence clearly states the purpose. However, it repeats 'read-only' three times, which could be reduced without loss of clarity.

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 has 7 parameters, 2 required, and an output schema, the description covers the key aspects: relationship to 'delegate', read-only nature, and most parameters. However, it omits explanation for 'working_dir' and 'timeout_s', which are not self-explanatory from the schema alone. The output schema exists, so return values are not required.

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?

The description adds significant meaning to 5 of the 7 parameters: 'cli' (agent ID, see capabilities), 'goal' (the objective), 'model' (optional), 'files' (paths in scope), and 'role' (implied as 'architect'). It does not explain 'working_dir' or 'timeout_s', but the schema coverage is 0%, so the description compensates well.

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 verb ('Ask') and the resource ('implementation plan for goal'), and specifies it is under the 'architect' persona and read-only. It distinguishes itself from the sibling tool 'delegate' by noting that 'delegate' is for write mode implementation.

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 explicitly contrasts with 'delegate' (write mode), indicating that 'plan' is for designing an approach rather than implementing. It also tells the user to see 'capabilities' for the 'cli' agent ID, providing clear context for when to use this tool.

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