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

Annotations cover the safety profile, yet the description still adds substantial non-obvious behavior: the yaml library's anchor/alias resolution, an alias-expansion cap against billion-laughs documents, duplicate keys refused, a 100 KB ceiling, and 400-with-parser-message for invalid input. It also explains the billing model (uncharged failures, first 25 free, repeats not free), which is exactly the kind of context annotations cannot express.

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?

Core purpose and the reverse-tool pointer are front-loaded, and most sentences carry real information. The inline example is wedged mid-paragraph and slightly disrupts flow, but nothing is truly extraneous.

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?

No output schema exists, and the description covers the meaningful output concerns: JSON as the result, error behavior (400 with parser message), and size limits. It stops short of describing output formatting details (indentation, key ordering, number/string fidelity), which an agent producing downstream comparisons might want.

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?

With one parameter at 100% schema coverage the baseline is 3, but the description supplies a concrete multi-line example exercising a list and booleans, which clarifies the accepted input shape beyond the schema's terse 'The YAML text'. It doesn't add anything else parameter-specific, so it stops short of a 5.

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?

Opens with a specific verb+resource ('Convert a YAML document ... into JSON') and enumerates the concrete input classes it handles (config files, Kubernetes manifests, OpenAPI specs, front matter). It also names the sibling that does the inverse (json_to_yaml), so the agent can distinguish the pair instantly.

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?

Explicitly states the use case ('Use before feeding YAML into a JSON-only tool or schema check') and routes the reverse case to json_to_yaml. The only mild gap is the absence of an explicit when-not condition, but the reverse-tool pointer effectively covers it.

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