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

The annotations already mark destructiveHint=true, but the description goes well beyond this by disclosing permanence, the invoiced-milestone refusal and its financial rationale, the required permission, and the hard rule that confirm/confirmation_phrase must never be agent-filled. This is exactly the behavioral context an agent needs before invoking 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: the first states the action, the second explains a critical refusal condition, and the third states permissions and the human-confirmation rule. Every sentence carries essential information and the most important warning is front-loaded.

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 destructive, permission-gated mutation tool with no output schema, the description covers permanence, refusal cases, permission requirements, and the human-in-the-loop constraint. No critical operational detail 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 coverage is 67% and the schema already documents that confirm and confirmation_phrase must be human-supplied. The description adds important operational semantics by explicitly instructing the agent never to fill these on its own initiative, reinforcing the human-gated nature of the parameters beyond the schema text.

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?

The description opens with 'PERMANENTLY delete a fixed-fee billing milestone', naming a specific verb, resource, and scope. It clearly distinguishes this from sibling tools like projects_update_billing_milestone and projects_delete_document by naming the exact object being deleted.

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 description gives clear operational context: it is for deleting fixed-fee billing milestones, and explicitly states that invoiced milestones are refused. It also states prerequisites ('Requires finance.edit') and a required human confirmation step. It does not explicitly name an alternative tool for editing rather than deleting, but the usage boundary is otherwise clear.

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