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

Annotations are minimal (readOnlyHint=false, destructiveHint=false), and the description adds real behavioral value: it returns a downloadable ZIP, applies auto-target per-file rules, and enforces tier-based file limits. The destructiveHint=false annotation is consistent with the description's implication that source files are not destroyed. No contradiction found.

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 tight sentences — purpose, target behavior, and tier limits — each earning its place, with the primary action front-loaded. The [category: convert] suffix is minor noise but does not detract.

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 batch tool with no output schema, the description covers the essential return shape ('download a ZIP of the results'), the failure model is covered in the schema's files parameter (_manifest.txt, skip-not-fatal), and tier limits are stated. Minor gaps remain — output filename behavior and mixed-type handling under a global target — but nothing that would prevent a correct invocation.

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 of 3 applies. The description reinforces the target parameter's dual mode (global format like 'pdf' vs per-extension override map) and adds auto-format examples, but this largely restates what the schema already documents for target and filenames. No meaningfully new parameter insight is added.

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 and resource: 'Convert many files in one request and download a ZIP of the results.' The batch + ZIP framing and concrete auto-target examples (docx→pdf, heic→jpg, mov→mp4) clearly distinguish it from single-file siblings like convert_file, convert_document, and convert_word_to_pdf.

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 opening 'Convert many files in one request' clearly signals the batch use case, and the tier limits (5 free vs 50 Business) give an agent concrete eligibility checks before invoking. However, it does not explicitly name alternatives or state when NOT to use it (e.g., for a single conversion), so the when-not guidance is left implied.

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