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

With no annotations, the description carries the burden and does disclose meaningful behavior: the tool returns the conversion engine, AI Deep Read need, accepted options, and fallback alternatives; it also explains accepted format identifiers. It does not explicitly state that the tool performs no conversion, but the 'before sending' phrasing strongly implies a non-mutating check.

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 sentences, each earning its place: purpose is front-loaded, returns are listed, and the format-input quirk is included. No filler.

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?

The description is sufficient for a read-only preflight tool with two simple parameters. It names the key return fields and the accepted input forms; it doesn't need an output schema because there isn't one and the textual coverage is adequate.

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?

The schema already describes the two params at 100% coverage, so baseline is 3. The description adds real value by explaining that values can be ids, extensions, or common names—information not present in the schema—which helps an agent construct correct inputs.

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 states a specific action—'Check whether one format can be converted to another'—and clearly distinguishes it from siblings like convert_file by noting it's done 'before sending a file.' It also lists the concrete output (engine, AI Deep Read need, options, alternatives), so an agent can tell exactly what this tool does.

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 tells the agent when to use it ('before sending a file'), which implies it precedes convert_file. However, it never names sibling alternatives or explains when to prefer list_formats/get_conversion, so it stops short of explicit when-not guidance.

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