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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds valuable context beyond that: it makes one outbound HTTP request, stores nothing, requires no authentication, shares a rate limit of 12 calls/hour/IP with grade_llms_txt, and returns a plain-text notice on limit. It also warns that the summary is model-generated and can be wrong on vague pages. This is substantial behavioral disclosure that helps the agent 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?

The description is appropriately sized and front-loaded. The first sentence gives the core purpose, followed by the interpretation nuance, usage trigger, and then behavioral details. Each sentence earns its place; nothing is wasted. It is not overly long for the amount of information it conveys, and it is well-structured for an agent to quickly parse.

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 tool with a single parameter, the description is remarkably complete. It covers what the tool does, how the output should be interpreted, when to use it, its side effects (HTTP request, no storage, no auth), the rate limit, and the potential for model error. Since there is no output schema, the description adequately explains the output format (2-3 sentence summary). The annotations cover safety, and the description fills all other gaps.

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 100%: the only parameter, 'domain', already has a clear description ('Bare domain to read, without protocol or path, e.g. acme.com'). The description does not add any meaning beyond the schema—it merely refers to 'the public domain you pass,' which is redundant. Since the schema fully covers the parameter, 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?

The description states a specific action (fetches a homepage), the resource (public homepage), and the output (a 2-3 sentence summary of what the company does and who it serves). It clearly distinguishes itself from siblings by emphasizing the cold-read approach and the no-outside-knowledge constraint, making the purpose unambiguous.

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?

The description explicitly says 'Use when a user asks how their site, or a competitor's, reads to an AI.' This gives a clear trigger condition. It does not explicitly list exclusions or alternative tools, but the usage context is sufficiently clear, and the mention of the shared rate limit with grade_llms_txt hints at when to be mindful of usage.

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