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

Annotations declare the safety profile (destructiveHint=true, idempotentHint=true), and the description adds genuinely new behavior the annotations cannot convey: a hard guard that rejects the call unless approval and criterion-completion preconditions hold, plus the warning that a refusal must not be reported to the client as completion. It omits what state the declaration itself mutates or how refusal surfaces.

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 short sentences, front-loaded with the action, then the guard, then the agent-facing consequence. No filler, and the most important constraint (the refusal) appears before the warning about it.

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?

An output schema exists, so return values need not be explained, and annotations cover the safety profile while the description covers gating and error handling. The remaining gap is parameter identification, which neither schema nor description resolves for the two UUIDs.

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 carries the full burden for two UUID parameters, yet it never names milestoneId or milestoneSetId nor clarifies which identifier scopes the lookup. It only refers to 'milestones' and 'that milestone' generically, leaving an agent to guess which UUID is which.

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 and resource ('State that a milestone is complete'), and the refusal preconditions (milestones approved, all acceptance criteria met) implicitly separate it from siblings like mark_work_done or approve_milestones. It does not explicitly name a sibling, so the differentiation is inferential rather than stated.

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 refusal conditions function as explicit preconditions: only call this once milestones are approved and every saved acceptance criterion is met. The third sentence gives downstream behavioral guidance about not relaying completion to the client on refusal. No alternative tool is named for the states where this one refuses.

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