Plan server build

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

Reinforces the readOnlyHint annotation with 'Changes nothing' and adds valuable non-obvious behaviors: reports all problems at once, reuses existing channels/roles, never duplicates. This goes beyond what annotations or schema alone convey.

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?

Four sentences, front-loaded with the core action and safety guarantee. Each sentence provides distinct value without redundancy or filler.

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 complex tool with nested schema and no output schema, the description covers purpose, validation scope, safety, and reuse behavior. It does not explicitly describe the returned build plan's structure or how to pass it to execute_build_plan, but the core usage is clear.

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 100%, so the schema already documents both parameters. The description adds context about composing the blueprint from the user request and optionally using a reference layout, but does not detail individual parameter behavior beyond the schema.

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 validates a blueprint and stages an ordered build plan, listing specific validations (Discord limits, name collisions, role references, feature requirements, bot permissions). It distinguishes from execution tools by explicitly noting 'Changes nothing.'

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?

Provides clear context that this is for the planning phase prior to actual changes, with guidance to compose the blueprint from the user's request. It does not explicitly name alternatives or when-not conditions, but the planning vs. execution distinction is evident from the description and sibling tools like execute_build_plan.

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