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

Annotations already cover the safety profile (not read-only, not destructive, not idempotent), and the description adds real behavioral context beyond them: this creates 'a new version' and is 'shown on open tabs', telling the agent the call has a visible side effect on other viewers. It stops short of stating required permissions or limits on repeated calls.

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 tight sentence with the action front-loaded and the behavioral consequence appended after the colon. No filler, nothing redundant.

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 full schema coverage, an output schema, and annotations present, the description covers what is needed to invoke the tool and notes the version-creation side effect. The remaining gap is sibling disambiguation against highlight_text, which matters for a tool family this crowded.

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 100%, so the schema already explains color defaults, the space/space_id alternative, and the text/after/before/block disambiguation fields in detail. The description adds nothing about parameters, so the baseline 3 applies.

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?

The description names a specific verb (highlight) and resource (words in a space) and ties it to a concrete analog ('as the viewer's Highlight button does'). It is clear on its own, but it never distinguishes itself from the sibling tool highlight_text, which sounds functionally identical, leaving the agent to guess which one to call.

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?

Usage is only implied: the viewer-button analogy suggests 'use when a reader would press Highlight'. There is no explicit when-to-use vs when-not, no mention of prerequisites such as edit rights, and no routing to highlight_text or delete_highlight for related operations.

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