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

Annotations already cover safety (readOnly=false, idempotent=true, destructive=false), and the description adds substantive consequences beyond them: status=retired drops it without finishing, done/retired advances the path to the next milestone, and 'Its steps are kept' clarifies no cascade deletion. This is exactly the kind of side-effect disclosure annotations cannot express.

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 terse sentences, front-loaded with the action and field list before the status semantics. No padding; every clause carries information an agent needs.

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 mutation tool with annotations covering the safety profile and no output schema, the description is nearly sufficient: it names the editable fields and the key status side-effects. Minor gaps remain around the meaning of non-status fields, but nothing critical to correct invocation is missing.

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 only 17% (only 'due' documents its YYYY-MM-DD format), so the description must compensate. It enumerates the mutable fields and partially explains 'status' via do/retire/done effects, but adds no meaning for 'metric', 'target', or the trivial 'milestoneId', leaving several parameters under-explained.

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 ('Change one milestone') and enumerates the exact editable fields (title, metric, target, due date, status), so the agent knows precisely what this tool mutates. It does not explicitly distinguish itself from the batch sibling set_milestones or edit_step, 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?

Usage is implied ('Change one milestone' contrasts implicitly with the batch set_milestones), but there is no explicit when-to-use guidance, prerequisites, or named alternative. The status semantics hint at intent but do not tell the agent when to pick this tool over siblings.

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