设置阶段状态

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

With no annotations, the description carries the full burden, and it does disclose a genuine side effect: setting P5 to done auto-completes the project, plus the P5-cannot-be-skipped restriction. It does not cover idempotency, whether earlier/later phases are affected when one is skipped, permission requirements, or error behavior.

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?

Two compact sentences, front-loaded with the action and the valid states, with the P5 constraint following. No filler and nothing redundant.

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 5-parameter mutation tool with no annotations and no output schema, the description covers the core state model and one critical business rule but leaves parameter semantics and failure modes undocumented. Adequate as a minimum, but clearly incomplete for the tool's 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 0%, so the description must compensate, and it largely does not: note and displayName are never mentioned, and phaseIdx indexing is left ambiguous (the text says 'P5' while the schema permits 0-5, six values). Only the status enum is echoed from the schema, adding no meaning beyond it.

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?

States a specific verb+resource (set phase status) and enumerates the accepted states (todo/doing/done/skipped), so the agent knows exactly what the call changes. It does not explicitly contrast itself with phase.list or other siblings, but the mutation semantics make the distinction obvious.

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?

Usage is implied rather than stated: the agent infers 'call this to change a phase's state', and one important constraint (P5 cannot be skipped) is given as a precondition. There is no explicit when-to-use/when-not or pointer to the complementary phase.list tool for reading state first.

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