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

Annotations already declare destructiveHint=true and openWorldHint=false, so the low bar applies. The description still adds real value by disclosing the cascade ("all its records") — the most consequential behavior beyond the annotation — and by mandating user confirmation, though it omits irreversibility/recoverability and permission requirements.

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?

Two sentences, no waste, and the destructive scope is front-loaded ahead of the confirmation instruction. Every word earns its place.

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 two-parameter destructive tool with no output schema, the description covers the two things an agent most needs: the blast radius (all records) and the confirmation requirement. The unresolved semantics of the "collection" identifier is the remaining gap.

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 50%: "site" is documented as slug or id, but "collection" has no description at all. The description does not clarify whether collection is a name, slug, or id, nor how it relates to site — so it fails to compensate for the coverage gap on the one ambiguous parameter.

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 collection") and adds scope: the deletion cascades to "all its records," which distinguishes it from delete_record (single record) and delete_site. It stops short of naming those siblings explicitly, so it does not fully earn a 5.

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?

"Confirm with the user first" gives a concrete pre-invocation behavior, but there is no guidance on when to delete a collection versus removing individual records with delete_record, nor any prerequisites (ownership, empty-vs-populated collections). Usage is implied rather than routed.

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