save deliverable

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

Annotations only declare it as a non-idempotent write with destructiveHint=true; the description adds the approval-gate refusal rule and an anti-hallucination warning ('do not invent a deliverable that was not saved'), which an agent cannot get from the structured fields. It does not, however, explain why the tool is flagged destructive or what the write replaces.

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, no padding, with the core purpose front-loaded. The middle sentence is slightly dense but every clause carries useful information.

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 the approval-gate behavior is covered. The remaining gap is parameter meaning: with 0% schema coverage and no parameter prose, an agent must guess the role of the two UUID fields.

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?

All four required parameters (milestoneSetId, milestoneId, title, detail) have 0% schema description coverage and the description explains none of them. 'Belongs to a milestone' only faintly hints at the milestoneId linkage and gives no identity/format guidance for the UUID pair or expected content for title/detail.

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: 'Save one deliverable that belongs to a milestone', which is distinct from the sibling resources save_work_item and save_acceptance_criterion. It does not explicitly differentiate itself from those siblings, so it stops short of a 5.

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 a concrete exclusion condition: after milestones are approved, an extra deliverable is refused until an accepted add_deliverable suggestion. That is real when-not guidance, though it never names the sibling tools an agent should prefer instead.

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