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

With annotations already covering the safety profile (readOnly, openWorld, idempotent, non-destructive), the description goes further: it discloses one outbound HTTP request, that nothing is stored, that no authentication is needed, and that a fair-use limit per IP is shared with cold_read with a plain-text notice on exhaustion. These are exactly the side effects an agent cannot infer from annotations alone.

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 action and output, then behavior, then usage guidance. Every sentence carries distinct information (fetch target, scoring, missing-file handling, trigger condition, side effects, auth, rate limits) with no repetition of structured fields.

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 no output schema, the description fully describes the return shape (0-100 score, per-check pass/miss as plain text, missing-file message with generator link, rate-limit notice). Combined with the single well-documented parameter and annotations, an agent has everything needed to invoke it 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 coverage is 100% and the parameter already documents 'bare domain, without protocol or path'. The description adds value by showing exactly how the domain is composed into https://<domain>/llms.txt, confirming the expected input form and revealing the fetch target. That is genuine added meaning, though modest.

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 (grades), the exact resource (https://<domain>/llms.txt), the mechanism (seven deterministic checks), and the output (0-100 score plus pass/miss per check). It also names the sibling it shares a quota with (cold_read), so an agent can place it among the other tools without ambiguity.

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?

Provides explicit trigger conditions: 'Use when a user asks whether a site is readable by AI assistants or wants their llms.txt reviewed.' It also covers the missing-file path and the rate-limit interaction with cold_read, giving the agent enough to route correctly and anticipate the limit notice.

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