propose_annotation_removal

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

With no annotations, the description carries the full burden, and it does disclose the key trait: the PDF is not modified. That is a meaningful behavioral claim. It does not say what the preview returns, whether the proposal is persisted or handed to apply_annotation_removal, or how errors on a missing xref are surfaced.

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?

A single sentence with no filler; the preview semantics and the non-mutation guarantee are both front-loaded where an agent will read them first.

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?

No output schema exists, so return-value explanation is not strictly required, and the non-destructive intent is clear. But with undocumented parameters and no annotation coverage, the definition leaves the agent guessing how to obtain a valid xref and what the preview actually produces.

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?

All three parameters (file, page, xref) have 0% schema description coverage, so the description must compensate and it does not. 'ONE existing highlight' hints that a single annotation is targeted, but nothing explains that xref is the annotation reference, how it is obtained (e.g., from list_annotations), or the page/file conventions.

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?

Specific verb ('Preview removal') plus a tightly scoped resource ('ONE existing highlight'), and the modifier 'without modifying the PDF' implicitly contrasts it with the apply-side siblings. It stops short of naming apply_annotation_removal directly, so sibling routing relies on inference from the propose/apply naming pattern.

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?

'Preview' implies the dry-run-before-apply workflow, which is adequate context for the propose/apply pair. However, it never states when to use this instead of apply_annotation_removal, nor any prerequisite (e.g., that a preview should precede the mutation).

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