PDF: highlight or underline text

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

Annotations declare a non-readonly, non-idempotent, non-destructive mutation, but the description adds substantial context beyond them: marks are saved under a distinct author, the note placement model (on the mark vs a margin icon replying to it), and critically 'The user must save Okular first or their unsaved marks are lost.' That save-state warning is exactly the kind of behavioral disclosure 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 core action and no filler sentences, but the remaining content is packed into one dense paragraph, mixing parameter details and a warning. Slightly denser than ideal, though every clause 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?

With an output schema present, return values need not be described, and the mutation behavior, note model, and save requirement are well covered. The only gap is that `path` semantics are never explained, leaving the agent to infer the target file.

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, and it documents text, note, page (default the shown page), color (full enum list plus default and strikeout override), style, and note_in_margin. Only `path` is left unexplained, so the coverage is strong but not total.

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 set (highlight, underline, squiggle, strike out) on a clear resource (a text passage in the PDF), and the title 'PDF: highlight or underline text' reinforces it. An agent can distinguish this from add_note, which adds a standalone note, without opening the schema.

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 actionable guidance: mark every occurrence of `text`, default to the shown page, and 'quote enough words to be unique.' It also frames note_in_margin as the least intrusive option. It stops short of explicitly routing between siblings like add_note or remove_annotation.

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