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

Annotations already mark destructiveHint and idempotentHint, but the description adds key behavioral traits beyond those: it is deterministic (no AI generation), it is the only way to record an intentionally-empty skills section, and a stale source_stage yields 409. The warning that a cleared draft cannot be published as a new plan is critical context not present in structured fields.

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 dense sentences with no filler: the core action is front-loaded, then the reason, then the caveats. Every sentence earns its place—the delete limitation, the publish restriction, and the source_stage concurrency behavior are all decision-relevant.

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 mutating clear operation, the description covers the key decision points: when to use it, what happens to the draft (can't publish), how to apply to live plans, and concurrency behavior. No output schema exists, but the invocation behavior is fully described and the effect is a deliberate clearing, so nothing is missing for correct selection and invocation.

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 0%, so the description carries the full burden. It explains the only non-obvious parameter, source_stage, including the stage const and the version-staleness 409 behavior. The generic wrapper parameters (action, resource, input) are self-evident from the schema consts/patterns, so the description adds meaning where it matters most.

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 states a specific verb ('clear') and resource ('every job skill from a draft') plus the resulting state ('leaving the stage deliberately empty'). It distinguishes itself from sibling delete_skills by citing that delete refuses the last skill, and from generate_skills by asserting it is deterministic with no AI generation.

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?

It explicitly names the alternative (delete) and explains the condition that makes this tool necessary: the delete refuses to remove the last skill. It also adds a workflow rule—the emptied draft cannot be published as a new plan—and directs the agent to modify_active for live plans, leaving no ambiguity about when to use this vs alternatives.

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