Zovo Place Card Maker

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real behavior on top: output layout (3.5 x 2 in flat cards, 10 per Letter/A4 page, crop marks), a second artifact (table plan PDF grouped by table with meal counts), and a hard limit of 300 guests. It also discloses a transformation expectation ("Convert the guest list into guests") that the agent must perform before calling.

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 condition is front-loaded, then outputs, then limits, in four dense sentences with no filler. "Convert the guest list into guests (name, table, meal)" mildly restates what the schema already spells out, costing a bit of tightness.

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 an 8-parameter, zero-required generation tool with a full schema, existing output schema, and read-only annotations, the description covers trigger, output artifacts, page geometry, guest cap, and the seat-assignment exclusion. Nothing an agent needs in order to call 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 description coverage is 100% and each parameter already carries its own enum-like options and defaults (size, sort, paper, show_meal, show_table, event_title), so the description's only added input signal is the guests-vs-text preference, which the schema itself already states. Baseline 3 applies when the schema does the heavy lifting.

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 and resource and even defines the artifact: "escort cards (flat cards that tell each guest their table, often with meal choice) or a printable table plan list from a guest list." The scope boundary "Does not choose seats for guests" is a useful disambiguator, but the sibling generate_place_cards is never named, so the agent must infer the escort-vs-place-card distinction on its own.

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?

"Use this when the user wants escort cards ... or a printable table plan list from a guest list" gives an explicit when-to-use trigger, and "Does not choose seats for guests" states a clear exclusion. It stops short of naming the alternative tool (generate_place_cards) or describing when that one should be preferred instead.

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?

Annotations already declare readOnly/idempotent/non-destructive, so the description's value is the added context it supplies: a 300-guest cap, long-name shrink-then-wrap behavior, back-face rotation, fold lines and crop marks, and the extra table plan PDF artifact. That is meaningful beyond the annotations, though it says nothing about what happens when inputs exceed limits or how failures surface.

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: the usage trigger leads, the conversion instruction follows, and the non-goal closes. It is a single dense paragraph with some duplication of physical specs already documented in the size and per_page fields, which keeps it from a 5 but does not make it wasteful.

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 9-parameter generator with full schema coverage and an output schema, everything an agent needs is present: input sources and precedence, limits, layout outcomes, optional fields, and scope exclusions. Return-value details are correctly omitted because the output schema covers them, apart from the useful note that a table plan PDF also comes back.

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% with well-written per-parameter descriptions, so the baseline is 3; the description earns above that by adding the conversion guidance ("guest list, spreadsheet or a photo of a seating chart into guests (name, table, meal)") and the default sorting logic. Some of the layout spec (3.5 x 2, 4 vs 6 per page) merely restates the size and per_page schema text.

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 names a specific verb+artifact ("Makes tent-fold cards") with exact dimensions, output formats, and an explicit negative scope ("Does not seat guests or design invitations"). It is unmistakably a place-card generator rather than a seating or invitation tool, though it never explicitly contrasts itself with the sibling generate_escort_cards, leaving that distinction to domain inference.

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 opening clause gives concrete when-to-use triggers (wedding, dinner, Thanksgiving; guest list, template, or table name cards) and the text parameter is framed as fallback-only with the preferred source named. What is missing is an explicit statement of when a user should pick the escort-card sibling instead.

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