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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the description doesn't need to re-argue safety. It does add genuinely new behavioral facts: output resolution (144 PPI), output encoding (Base64 data URI), and the stateless no-persistence contract. Rate limits and size limits for large documents are not mentioned, which keeps it off a 5.

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?

Two sentences, front-loaded with the operation and output format, with the example placed last where it aids rather than delays comprehension. No filler or restatement of the tool name.

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?

An output schema exists, so return-value structure need not be explained, and the description still usefully names the Base64 PNG form. Annotations cover the safety profile. The remaining gap is workflow context: with 37 overlapping parameters shared across generate_document and convert_document, the description should say when a preview is preferred over a generated file.

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 description coverage is 100%, so all 37 parameters are already documented with per-field descriptions and 8 enums. The description contributes only a single example call exercising doc_type, from, and to; it adds no guidance on interaction between the many optional formatting flags. Baseline 3 applies when the schema carries the load.

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 concrete verb and output artifact: render a 144-PPI PNG preview as a Base64 data URI, statelessly. That is far more specific than the title alone. However, it never names or contrasts itself with generate_document or convert_document, which share the same 37-parameter payload, so an agent cannot tell from the description which of the three to pick.

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 phrase 'statelessly ... without mutating server records' implies this is the read-only preview path versus a persisting generate step, and the inline example shows a minimal valid call. But there is no explicit when-to-use/when-not-to-use statement and no mention of the sibling generate_document or convert_document, leaving the routing decision to inference.

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