Clear processed underlines

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

Annotations already declare destructiveHint=true and idempotentHint=true, so safety is covered; the description adds genuinely new behavior beyond them — permanent, irreversible deletion and a filtering rule that silently skips non-gray ids. It does not describe how skipped ids are reported back, keeping it at 4.

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 short paragraphs with zero filler; the destructive nature and the precondition are both front-loaded before the detail.

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, low-parameter mutation with full schema coverage, complete annotations, and an output schema, the description supplies everything else an agent needs: irreversibility, the approval precondition, and the id-filtering rule.

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 the baseline is 3, but the description adds real meaning: the ids are validated against gray-underline status and are the exact set deleted. It also clarifies document scope ('the Skim document') beyond the schema's default-to-front-document note.

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 (PERMANENTLY DELETE) and resource (processed/gray underlines) with an explicit scope qualifier (by id) and notes it MODIFIES the Skim document. This cleanly separates it from read-only siblings like get_pending_underlines and the non-destructive mark_processed.

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 a clear precondition ('Only run after the reader has explicitly approved clearing these ids') and a when-not rule ('pending (red) underlines, highlights and other markup are skipped'). It does not explicitly route to a sibling alternative, so it falls just short of a full 5.

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