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

The description goes well beyond annotations by disclosing that the operation is deterministic, prunes behavioral anchors in the same write, reports the pruned ids, and makes the draft unpublishable as a new plan. It also explains the 409 stale-version behavior. This adds substantial behavioral context beyond readOnly/destructive/idempotent hints.

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 with no filler. The primary action is front-loaded, and each sentence adds a distinct, useful fact: determinism, anchor pruning, publication restriction, and staleness behavior. It is dense but appropriately sized.

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 draft-mutation tool with no output schema, the description is unusually complete: it covers the operation, side effects, returned information, publication constraints, the recommended alternative, and the stale version failure mode. An agent has enough to call it correctly and avoid the main pitfalls.

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 burden. It usefully explains source_stage semantics and its stale-version 409 behavior. However, it does not clarify what happens when source_stage is omitted, and it does not add meaningful explanations for request_id or idempotency_key, though those are standard and partly self-evident.

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 action and resource: 'Clear every competency from a draft' and adds the key distinction 'deterministic, no AI generation.' It clearly separates this from generate_competencies and delete_competencies siblings by emphasizing it clears all competencies and prunes anchors, not just individual ones.

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 explicit usage context: the emptied draft cannot be published as a new plan, and the intended alternative path is to 'bind the emptying onto an already-live plan with modify_active.' It also warns about the stale source_stage returning 409. It does not explicitly contrast with delete_competencies for partial removal, but the guidance is clear enough for most selection decisions.

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