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

Annotations only declare readOnlyHint=true; the description goes well beyond that with the 6 MB input ceiling, the lower 1 MB ceiling when the target is Markdown, the guarantee that nothing is stored, and the 1-credit-per-call cost. Those are exactly the operational facts an agent needs before committing a payload. This is substantive disclosure layered on top of the annotation rather than a restatement of it.

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?

It is front-loaded with the purpose and then the routing list, and the constraints (size caps, no storage, cost) come last where they belong. The conversion list is long but functional rather than padded. Slight tightening is possible — 'a Word document (.docx)' and the format enumeration could be more compact — but essentially every clause earns its place.

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 five-parameter, single-action tool with no output schema and minimal annotations, the description covers purpose, accepted inputs, limits, privacy and cost. What it leaves out is failure and return behavior — unsupported pairs are only surfaced in the schema's 'to' description, and the description never says what a successful response contains. That is a real but minor gap given the schema fills it.

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%, including the 'exactly one of text, url or file_base64' constraint and the note that text is invalid for docx, so the schema already carries the parameter semantics. The description restates the three input paths ('a URL or base64, or paste the text') and adds nothing about format casing or accepted MIME variants. Baseline 3 is appropriate.

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 uses a specific verb ('convert') and resource, and enumerates the exact supported conversion pairs (docx→HTML/Markdown/text, HTML→Markdown/text, Markdown→HTML, CSV↔JSON, CSV/TSV both ways). That matrix effectively tells an agent what the tool does and implicitly separates it from text-only siblings. It stops short of naming a sibling to avoid, and the near-neighbor url_markdown is never acknowledged, so a 4 rather than a 5.

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 trigger condition is stated explicitly: 'Use when a task has a file in one format and needs it in another', followed by the exhaustive list of pairs that qualify. There are no exclusions, no statement about when to prefer a different tool, and no note that unsupported pairs (e.g. JSON→TSV) will fail, so it gives clear context without routing guidance.

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