Create milestone

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

The description adds valuable behavioral details beyond annotations: it is additive, performs readback of the created milestone, avoids automatic retries on ambiguity, and does not affect issues or existing milestones. This aligns with annotations (non-read-only, non-idempotent, non-destructive) with no contradictions.

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?

The description is three sentences, front-loaded with the primary action and followed by important clarifications. It is slightly verbose but each sentence conveys essential information without excessive padding.

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?

Given the rich annotations and schema descriptions, the description provides sufficient additional context about operational behavior (readback, no retries, no assignment) to fully understand the tool's scope and edge cases.

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?

The description mentions title, description, due date, and state, which cover most parameters, but does not explicitly address owner and repo (though these are standard). Bounds are referenced but not specified beyond schema constraints, adding some value without redundancy.

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 clearly states the tool creates exactly one repository milestone with specific fields (title, description, due date, state). It also distinguishes from siblings by noting it does not assign issues or edit existing milestones.

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 implicit usage context ('after ordinary write authorization', 'never retried automatically') and clarifies it does not edit or assign, but does not explicitly name alternative tools or provide a clear 'use this instead of X' directive.

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