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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is largely covered. The description reinforces this with 'This cannot be undone' and adds the reader-scope detail, but doesn't disclose what happens on an unknown or already-deleted ID, which matters for a destructive call.

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 compact sentences with the action and its scope front-loaded and the irreversibility warning placed last for emphasis. No filler or redundant phrasing.

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 one-parameter delete with rich annotations and no output schema, this covers what is deleted, where it lives, where the ID comes from, and that it is irreversible. The only notable gap is behavior for an invalid or already-removed highlightId.

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% for the single highlightId parameter, so the description must carry the meaning. It does add real value by pointing to list_notes as the source and tying the ID to highlights/bookmarks in the in-app reader, but it gives no format or constraint detail beyond the schema's length bounds.

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 ('Deletes a highlight or bookmark') and scopes it to 'made in the in-app reader', which separates it from note and shelf operations. It stops short of naming siblings like edit_highlight or delete_note, so differentiation is implied rather than explicit.

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?

Provides clear context for when to call it: removing an existing in-app reader highlight or bookmark, with the ID sourced from list_notes. There are no explicit exclusions (e.g., 'use edit_highlight to modify instead') or error-handling guidance, keeping it below a 5.

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