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

Annotations only cover the safety/mutability profile (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false); the description adds substantial behavioral context on top: per-word credit cost, the 6,000-word refusal threshold, 10-90s latency, preservation guarantees for headings, facts, prices, legal lines and button labels, the ±20% length constraint, and the exact backend endpoint.

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, then layered with constraints, cost, latency, output shape, and presentation guidance — essentially every clause carries information. It is a single dense paragraph that runs long, so it is efficient but not maximally scannable.

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?

There is no output schema, and the description compensates fully by listing the return payload (ordered blocks with original + rewritten, whole-page markdown, voice-match and AI-tell scores before and after). With annotations covering safety and the description covering cost, limits, latency, and returns, an agent has everything needed to call and present this tool correctly.

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 67% and the schema already documents url and continuity in detail. The description only implies profile_id via 'the profile's voice' and says nothing about the continuity flag, so it adds marginal meaning beyond the structured fields — baseline 3 is appropriate.

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 ('Rewrite a public web page's copy in the profile's voice, block by block') and scopes it to public pages with the page's own context used as prompt material. An agent can distinguish this from humanize, polish, or generate_content 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 concrete gating conditions: paid plans only, pages over 6,000 words refused, and it tells the agent how to present results ('Show the user a few before/after blocks, not the whole deck'). It never names an alternative sibling (humanize, polish, mimic_brand) or states when not to use this tool, so it stops short of full alternative routing.

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