Label sheets PDF

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

Annotations already declare readOnly/idempotent/closed-world, so the bar is lower, and the description still adds real behavioral context: hard cap of 3000 labels, Latin text only, shrink-to-fit stepping down to 5 pt, printer offset nudges in mm, and the practical instruction to print at 100% / actual size. It omits what the call actually produces (a written PDF file and its path) and any note about multi-sheet output.

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?

The most decision-relevant information (what it prints, mode semantics, limits) is front-loaded, and there is no filler. It is a single dense run-on paragraph with slash-and-parenthesis packing, which is efficient but slightly harder to scan than a short bulleted form.

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 22-parameter, zero-required-parameter generator with no output schema, the description covers geometry, text input modes, typography, and limits well. The remaining gap is the return contract: it never states that the result is a PDF file path (or base64 when returnBase64 is set), which the agent needs to chain further processing steps.

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 already 86%, so the baseline is 3; the description nonetheless adds value beyond the schema by mapping presets to real stationery codes (L7160, L7159, L7163, L7654, L7651, 5160/5163/5167) and giving a concrete template example "{Name}\n{Street}\n{City} {Postcode}". It does not clarify interplay between "count" (same mode) and "copies" (list/csv), which is the one genuinely ambiguous pair.

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?

Opens with a specific verb and resource ("Print address or product labels on standard sticker sheets as PDF") and then enumerates the exact sheet families and modes, so an agent knows precisely what artifact it gets. No sibling tool in the list produces label sheets, and the tool name/title are fully substantiated rather than restated.

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?

Usage is expressed at the mode level: "list" (one label per block, blank line between), "csv" (rows into a template, header or {1} style), "same" (one text × count), plus a note to start at a later position to reuse a part-used sheet. What is missing is an explicit statement of when not to use it (e.g. vs. doc_business_cards or doc_invoice) or prerequisites such as the Latin-only constraint being called out as a blocker rather than a footnote.

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