convert_to_markdown

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety and network reach are covered. The description adds genuine processing context (PDF layout analysis, table structure extraction, OCR, audio and image handling) that annotations don't convey, but it says nothing about size limits, fetch/auth behavior for remote URIs, or failure modes on unsupported inputs.

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?

Front-loaded with the core verb-resource-output statement in the first clause, then a compact parenthetical covering formats. The final sentence about MarkItDown is near-filler, but the overall shape is tight and skimmable.

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 one-parameter tool with no output schema, the essentials (input forms, output format, supported file types) are present, but the description never characterizes the returned payload or how conversion failures surface. Adequate but with clear gaps given there is no output schema to fall back on.

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 a single parameter and 100% schema description coverage, the schema already documents valid URI forms and relative-path resolution against the server root. The description adds the catalogue of supported file types but no new syntax, defaults, or constraints for the 'uri' argument itself, so the baseline 3 applies.

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 (convert) and resource (a document addressed by http/https/file/data URI or local path) plus the output format (Markdown), so an agent knows exactly what the tool produces. It does not, however, differentiate itself from the sibling tool 'convert', and the trailing note that it mirrors MarkItDown's tool of the same name is provenance rather than differentiation.

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 lists the input kinds supported but never says when to prefer this over the sibling 'convert' or when to consult 'list_input_formats'. There is no stated exclusion, precondition, or alternative-selection rule, leaving routing to inference.

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