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

Annotations already declare readOnlyHint, openWorldHint=false, idempotentHint and destructiveHint=false, so the safety profile is covered. The description still earns credit by spelling out the practical consequences — no link fetching, no persistence, no publishing — which tells the agent this is a pure, side-effect-free evaluation of input it already holds.

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?

Three short sentences, front-loaded with the action and scope, followed by two clarifying constraints. 'Required format is separate from writing recommendations' is slightly abstract phrasing, but nothing is padded or redundant.

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?

With an output schema present, return values need no explanation, and annotations cover the mutability profile; the description fills the remaining gap by establishing the in-memory, no-network, no-persistence contract. The only shortfall is that it does not define what 'required format' validation actually checks, leaving the agent unsure what kinds of errors will be reported.

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 0% for the single 'text' parameter, so the description carries the burden. 'Pasted llms.txt draft' does convey that the parameter is the raw document content rather than a URL or ID, but it says nothing about size limits (524288 chars) or whether the value must be the complete file. Marginal compensation for the coverage gap.

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 ('Check a pasted llms.txt draft') plus the scope qualifier 'in memory', which separates it from tools that act on stored or fetched content. It never names check_llms_txt or read_llms_txt explicitly, so the differentiation must be inferred from the 'pasted' and 'no links fetched' phrasing.

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?

'Check a pasted llms.txt draft in memory' and the note that the required format is distinct from writing recommendations imply the use case: validating user-supplied text rather than generating or auditing a live site. However, no sibling is named and there is no explicit 'use X instead when you have a URL' routing, which matters given check_llms_txt and read_llms_txt sit right next to it.

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