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

Annotations already declare the write/non-idempotent/non-destructive profile, and the description adds real behavioral context beyond that: input is validated ('abstract steps are rejected') and ordering violations produce a warning ('warns otherwise'). It stops short of naming the failure mode or the response shape.

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?

Front-loads the action, then layers the acceptance rule and ordering rule compactly. Every sentence carries content, though the trailing 'warns otherwise' is clipped enough to be slightly ambiguous.

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 3-param mutation tool with no output schema and no documented return value, the description covers validation and ordering but omits prerequisites, what the call returns (created step ids?), and how partial failures in a multi-step array are handled.

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 only 33% (only op_id is documented), so the description must compensate. It conveys domain meaning for steps (concrete, work-block-sized, lever ordering) but never maps to the actual fields milestoneId, title, leverId, or estimateMin. Partial conceptual coverage only.

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 ('Add concrete steps to a milestone') and immediately qualifies what a valid step is versus an invalid one ('email 10 people from the waitlist', not 'do marketing'). An agent can distinguish this from edit_step/delete_step/next_steps from the description alone.

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?

Gives strong in-tool guidance (abstract steps are rejected; hard-lever step first; preparation only where it blocks) but never says when to choose this over a sibling like edit_step or when not to call it. Usage context is implied rather than explicit.

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