Zovo Envelope Printer

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

Annotations already declare this is a read-only, idempotent, closed-world lookup, and the description adds substantive behavior beyond that: fitting results are constrained to envelopes with at least 1/8 in clearance and ordered smallest first, and envelope lookups return inches, mm, intended use, and USPS mail shape. Those details materially shape how an agent interprets and relays results.

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?

Front-loaded with the routing trigger, then the two behaviors, then the boundaries — a sensible order with no filler. The long parenthetical of quoted example queries is dense but each phrase earns its place as a matching cue for an agent parsing user phrasing.

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 three-parameter lookup with an output schema and full annotations, the description covers what an agent needs: when to call it, what each input mode yields, result ordering and fit tolerance, and the two things it will not do. Nothing required for correct invocation is missing.

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 alone carries the mechanics; the description still adds semantic framing by contrasting the two modes (give a card/photo/folded sheet size vs. give an envelope name) and mapping them onto the free-text query versus the width/height pair. It stops short of stating precedence when both query and width/height are supplied.

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+resource (find envelope size) and immediately grounds it in the user phrasings it answers ("#10 envelope size", "a7 envelope size"). It also pins down the two input modes — size given → matching envelopes, envelope name given → its dimensions — which no sibling shares.

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?

Opens with an explicit when-to-use trigger ("Use this when the user asks what size envelope to use or how big an envelope is") and names the alternative for the adjacent case: "Does not print anything (use generate_envelope_pdf)". It also excludes a plausible but out-of-scope adjacent request (postage prices).

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

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

Beyond the readOnly/idempotent/non-destructive annotations, it discloses layout behavior (return address top-left, delivery address in the USPS read area, destination-country line order), per-address page generation, that problems like missing ZIP or wrapped lines are reported back, and that a CSV is also produced. The explicit negative capabilities further bound the tool's behavior.

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 a single dense paragraph, but the trigger condition and exclusions are front- and back-loaded correctly and every clause carries informational weight. The long parenthetical list of utterance examples is somewhat bulky.

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 19-parameter tool with nested objects, an output schema, and existing annotations, the description covers purpose, input preparation, sizing defaults, layout, error reporting, and scope exclusions. Nothing required to invoke it correctly is missing.

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 is 3, but the description adds real meaning: the default #10 size and the full size vocabulary including custom sizes, and the instruction to first convert pasted text or images into recipients objects before calling. It does not walk through the many formatting flags, but the schema already documents those thoroughly.

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 opens with a specific verb and resource ('print addresses on envelopes') plus concrete trigger phrasings, and states precisely what is produced ('Makes a PDF with one page per envelope at the real envelope size'). It never references the sibling find_envelope_size, so the boundary with that tool is left implicit rather than stated.

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 gives an explicit when-to-use trigger ('Use this when the user wants to print addresses on envelopes') with six example utterances, plus a clear when-not list: no postage purchase, no stamps or barcodes, no address verification, no label sheets. An agent can decide to call or skip without inference.

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