propose_annotation_update

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

With no annotations provided, the description carries the full burden, and it clearly discloses the key safety trait: this is a preview that makes no changes. It does not describe what the proposal artifact contains or whether it expires/is tied to a later apply, so the disclosure is good but not exhaustive.

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 sentences with zero filler; the scope constraint and the no-edit guarantee are front-loaded. 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?

For a 5-parameter tool with no annotations, no output schema and 0% schema coverage, the description covers intent, a key parameter source and the non-destructive behavior, but says nothing about the returned proposal or how it links to the subsequent apply call. Adequate but with a clear 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 description coverage is 0% for 5 parameters, so the description must compensate. It specifies the two mutable fields (color, opacity) and points the agent at list_annotations as the source of page and xref, but file semantics are left entirely to the schema and no format hints (color encoding, opacity range) are given.

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 ("Preview changing"), a scoped resource ("ONE existing highlight") and the exact fields involved (color or opacity), with "no edits" explicitly separating it from the apply_annotation_update sibling. An agent can distinguish this from apply_annotation_update and propose_highlight without opening any 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 a concrete prerequisite ("Obtain page and xref from list_annotations") and an ordering instruction ("Review the proposed edit first"), which effectively frames the propose-then-apply workflow. It does not name apply_annotation_update as the follow-up tool, so the alternative is implied rather than stated.

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