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

Annotations already declare a safe, idempotent, non-open-world read, so the bar is low, yet the description adds substantial behavior: fractions preserved rather than decimalized, unit conversion only on request, long recipes spilling to a second card instead of shrinking below 8 pt, cut lines, and returned scaled lines plus card counts and a PDF link. That is real operational context an agent could not infer from the hints.

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 trigger phrase and the main action are front-loaded, and each sentence carries either a trigger, a preprocessing rule, or a behavior. It is dense but readable; the parenthetical list of card phrasings and the return-value sentence are slightly padded given an output schema exists.

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 14-parameter tool with optional everything, the description covers the decision to call, the ingestion path for pasted or photographed recipes, supported sizes and layouts, scaling and unit rules, and explicit non-goals. With an output schema present, the brief return summary is sufficient rather than necessary.

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 schema already documents card_size, paper, units, scale, orientation and the single-recipe shortcut fields. The description's mentions of the same card sizes and the keep/metric/us behavior largely restate the schema, adding only the 4-per-sheet and 8 pt layout constraints, which the paper field already gestures at. 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 states a specific verb and artifact ("Builds a PDF of 4x6, 3x5, 5x7, half-letter or A6 cards") plus the scaling function, and explicitly delimits scope with "Does not find or invent recipes, does not compute nutrition, and does not change cooking times." An agent knows exactly what this produces without opening the schema.

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?

It opens with an explicit trigger list ("recipe card", "4x6 recipe card", "print my recipe on a card", doubled/halved/scaled for printing) and gives a concrete pre-call procedure: copy title, servings, ingredient lines and steps into recipes, keeping amounts as written. Negative conditions (no recipe invention, no nutrition, no time changes) rule out the closest misuses.

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