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

Annotations already declare destructive=true, idempotent=false, and openWorld=true, so the description's job is added context. It delivers that: optimistic concurrency via expectedVersion, conflict recovery behavior, an untrusted-source warning, and the non-obvious side effect that omitting styleRef clears recorded style attribution rather than CSS. It stops short of stating the concrete blast radius of the replace (e.g. what happens to existing page content/versions).

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 URL guarantee, then workflow and caveats in tight imperative clauses. Slightly dense and mildly repetitive ('review' appears twice), but nearly every sentence carries an actionable instruction.

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 six-parameter destructive mutation with no output schema, the description covers the important operational edges: concurrency control, conflict handling, approval gating, and the styleRef side effect. It is only incomplete on the remaining input semantics (html/title/generationId) and what a successful replacement returns or invalidates.

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 only 17%, so the description must carry more weight. It usefully explains where expectedVersion comes from (get_page) and the omission semantics of styleRef, but html, title, pageId, and generationId get no treatment at all, leaving roughly half the parameters semantically thin.

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+resource with scope: 'Replace a page with new static HTML while preserving its shareable URL.' The replace-semantics-and-URL-preservation detail cleanly separates it from publish_page, unpublish_page, and set_artifact_style without opening their schemas.

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 explicit routing: use get_page's includeHtmlSource for presentations, the authoring file otherwise, and 'expectedVersion from get_page'. It also names the failure path ('On conflict, reread and review') and the review/approval precondition, leaving nothing to inference.

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