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

Annotations already declare read-only, idempotent, open-world and non-destructive, and the description adds substantial extra behavior: it reads one page and tests a few links, respects robots.txt for Agent Tools, does not execute JavaScript, and does not return page copy, review text or contact details. It also enumerates what the twelve checks return (status plus evidence plus fix), which is exactly the context an agent needs to set expectations.

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?

Purpose and usage triggers are front-loaded, then capabilities, then limitations, which is a sensible order. The enumeration of twelve checks is long but each item is a distinct, decision-relevant capability rather than filler; the description is dense without being padded.

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?

Despite an output schema existing, the description still sketches the return shape (status, evidence, fix across twelve named checks) and closes every ambiguity an agent would face: JS not executed, robots.txt honored, no copy/contact data returned, checklist rather than conversion prediction. Nothing needed to invoke or interpret the tool is missing.

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% for the single url parameter, and the schema already documents the bare-domain-means-https rule and the public/standard-port restriction. The description's 'Pass the page address' and its private/local-address exclusion reinforce the schema but add no new syntax or format detail, so the baseline of 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?

States a specific verb and resource ('Checks a landing page for conversion problems') and immediately distinguishes itself from siblings like check_page_tags, link_sample_check and ai_readiness_check by naming the twelve conversion-specific checks it performs. An agent can tell exactly what this tool covers 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?

Gives explicit when-to-use triggers with three natural-language example prompts, plus explicit exclusions: 'Do not use it for private or local addresses, rankings or traffic' and 'not a speed or design test'. This is the strongest possible routing guidance.

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