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

No annotations are provided, so the description must disclose behavioral traits. It states the tool extracts links, implying a read-only operation, but does not explicitly confirm non-destructiveness or discuss error cases (e.g., missing message). The classification aspect ('class guess') adds some value, but transparency is incomplete.

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 two sentences, with the first sentence clearly stating the tool's function and the second providing usage guidance. Every word adds value, no redundancy, and key info is front-loaded.

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 simple one-parameter tool with no output schema, the description adequately covers purpose, parameter source, output details, and an alternative tool. It feels complete and leaves no obvious gaps for an agent to misunderstand.

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% for the single parameter, but the description adds meaning by specifying the parameter comes from list_messages or wait_for_message, which is not in the schema. It also describes the output format (anchor text and class guess), going beyond the bare schema definition.

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 clearly states it extracts all links from a single message, including anchor text and class guesses. It distinguishes itself from wait_for_link by advising to use that tool when still waiting for the email. The verb 'extracted' implies retrieval, but a more explicit verb like 'get' or 'list' would be clearer.

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 advises preferring wait_for_link if still waiting for the email, which is a clear alternative. It does not mention other exclusions or prerequisites, but the guidance is specific and helpful for choosing between tools.

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