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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety and locality are covered. The description still adds valuable behavioral detail beyond them by explaining exactly what the response varies on — target formats for a given source, or the full set of source formats when omitted — which is what an agent needs to interpret the result.

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 with zero filler: the purpose comes first, the mode behavior second, the usage rule last. Every sentence contributes information an agent needs to select and call the tool.

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 single-optional-parameter read-only tool with no output schema, the description covers purpose, mode behavior, and follow-up workflow. The only soft gap is that it does not say whether formats are returned as bare extensions or with human-readable labels, but that is minor given the tool's simplicity.

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%, so the baseline would be 3, but the description earns more: it clarifies that `from` is a source format that pivots the output to target formats, and that omitting it changes the result set entirely. The schema only says "Source format extension... Optional" and never describes that output-shaping effect.

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 names a specific verb and resource ("List the formats MiConvert converts between") and then precisely differentiates the two operating modes of the tool: with `from` it returns targets for that source, without it returns every source. An agent can immediately tell this is the capability-discovery tool rather than a conversion executor like convert_file.

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?

It gives an explicit usage rule: "Use it to check that a conversion exists before calling convert_file," which names the relevant sibling and the precondition it serves. It does not state any when-not-to-use condition, but for a read-only lookup tool there is little ambiguity to resolve beyond that.

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