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

Annotations already declare readOnlyHint=false, destructiveHint=true, idempotentHint=false and openWorldHint=false, so the write/safety profile is covered. The description adds genuinely new behavioral context beyond that: the post-approval refusal rule and the dependency on an accepted add_criterion suggestion. It does not explain why destructiveHint is true or what is overwritten on repeated saves.

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 tight sentences with the core purpose front-loaded, followed by the gating constraint and the non-completion clarification. No filler, no restatement of the title.

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 no explanation, and annotations cover the safety profile; the description supplies the non-obvious refusal rule an agent would otherwise trip over. The remaining gap is parameter guidance for a 0%-coverage schema, which is scored separately.

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% across three required parameters (milestoneSetId, milestoneId, statement), so the description carries the full burden of explaining them. It says nothing about the distinction between milestoneSetId and milestoneId or the 500-character statement limit, adding no meaning beyond the bare parameter names.

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 ('Save one acceptance criterion') and defines the resource's meaning ('what done means for that milestone'). It implicitly differentiates from save_deliverable/save_work_item by defining the artifact, but never explicitly contrasts them, so sibling differentiation is soft rather than sharp.

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?

Gives a concrete when-not condition ('after milestones are approved, a new criterion is refused until an accepted add_criterion suggestion') and a disambiguation ('This does not mark the milestone complete'), which steers agents away from declare_milestone_complete. It lacks an explicit positive trigger statement ('use when defining done criteria for a not-yet-approved milestone'), leaving part of the routing to inference.

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