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

Beyond the readOnlyHint annotation, it discloses truncation caps (≤20 changed pages, ≤10 blocks each), that output is meant to be shown to a human before mutation, and a prompt-injection warning that page text is data not instructions. These are behavioral traits an agent could not infer from the annotations.

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-loads read-only status, then the comparison direction, then output shape, then the operational instruction. Dense with parenthetical qualifiers rather than prose sprawl; no sentence is filler.

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 no output schema, the description carries the return-value burden and does so: files added/removed/changed and per-page detail with explicit caps. The safety profile and next-step guidance are included, so an agent can call and act on it without further context.

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 coverage is already 100%, so baseline is 3; the description adds the provenance of the 'to' value (a deploy id from list_versions) and restates the accepted forms. It largely mirrors the schema but the sourcing hint carries modest extra meaning.

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 (diff between two versions) plus the scope involved (deploy:write), and anchors the 'to' argument to sibling tools. An agent can tell this apart from preview_version or list_versions 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?

Explicitly directs use before rollback or publish_draft — naming the downstream siblings this feeds — and specifies where 'to' values come from (list_versions, live, draft, draft:<n>). Both the when and the value source are stated outright.

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