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

Beyond the annotations (destructiveHint=true, idempotentHint=true), the description discloses concrete side effects: behavioral anchors are pruned in the same write and pruned ids are reported, the stage must retain at least one competency, and optional source_stage causes a 409 on stale version. This meaningfully exceeds what annotations alone convey and is consistent with destructiveHint=true.

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 with no filler: the core operation is front-loaded, followed by side-effect and invariant details, then the optional concurrency behavior. Every sentence adds decision-relevant information.

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 nested-parameter tool with no output schema, the description covers the return signal (pruned ids), the key invariant (at least one competency), the write scope (anchors pruned atomically), and the concurrency failure mode (409 stale). No critical behavioral gap remains for an agent deciding whether and how to call it.

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 schema prose coverage at 0%, the description carries the semantic burden and does so well for the key parameters: "by id" maps to the required ids array, and "source_stage {stage: competencies, version} returns 409 when stale" explains the purpose of the optional concurrency object. It does not enumerate every wrapper field (action, resource, request_id, idempotency_key), but those are fixed or conventional and largely self-evident from the schema.

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 a specific verb and resource: "Delete draft competencies by id," and immediately distinguishes this from bulk operations like clear_competencies by emphasizing targeted deletion. It also adds unique behavioral details (pruning anchors, one-competency minimum) that make the tool's purpose unambiguous among many interview-plan siblings.

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 clearly implies when to use it: to delete specific competencies by id rather than clearing all, and it encodes the invariant that at least one competency must remain. It does not explicitly name an alternative sibling like clear_competencies, so the guidance is clear context without an explicit exclusionary routing statement.

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