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

Annotations already flag destructiveHint=true and idempotentHint=true, and the description adds the concrete consequence beyond them: omitting an existing id deletes that milestone's steps. This spells out exactly what gets destroyed, which is the highest-value context for a destructive tool.

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 sentences, front-loaded with the replacement action, then the destructive rule, then the alternative. No filler; every sentence carries a distinct instruction.

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 single nested-array mutation with no output schema, the description covers replacement semantics, cardinality, deadline constraint and cascade deletion. Failure behavior and required permissions are unstated but minor given the annotations carry the safety profile.

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?

With 0% schema description coverage, the description must carry the semantics, and it does: cardinality (2–6), ordering, the requirement that due precede the goal deadline, and the meaning of id as the existing milestone identifier. It does not explain metric/target units or types, leaving a small gap.

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 ('Replace the list of 2–6 ordered milestones under the goal') and pins down the shape (metric, target, due before the goal deadline). It explicitly distinguishes itself from the sibling edit_milestone, so an agent can route without opening either schema.

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?

Names the alternative edit_milestone with the condition that selects it ('To change one milestone'), and states the replace-the-whole-list intent plus the id-passing rule. Clear context, though it doesn't enumerate broader when-not conditions (e.g. vs set_goal).

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