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

destructiveHint=true is already declared, but the description goes well beyond it: what survives a delete (posts, children), the two distinct blockages and why each exists ('that binding would otherwise stay pointing at nothing'), and that force leaves a rule dangling. This is exactly the context annotations cannot convey.

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-loaded with the effect, then the refusal cases in order of escalation. Dense but every clause carries information; only the trailing 'Rules: get-skill-doc' line reads as an appended afterthought rather than part of the flow.

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, refusal-prone tool this covers side effects, pre-flight checks, both failure modes with remedies, and escalation via force. An output schema exists, so no return-value explanation is needed.

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 100%, so baseline would be 3, but the description adds decision-level meaning to `force`: it applies only to a content-source body rule and explicitly does NOT cover the frame binding, which must be released via assign-template-archive. That scoping nuance is worth more than the schema alone.

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 (delete a term) plus the exact consequences: posts lose the label, children re-parent upward. Those effects distinguish it from siblings like delete-taxonomy and delete-content without needing the schemas.

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 explicit prerequisites (check `count` via list-terms, read get-skill-doc content-model-contract before the first call) and two named refusal conditions with prescribed remedies: unbind with assign-template-archive, or remove the content-source rule / pass force:true. An agent knows both when to call it and when it will be rejected.

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