generate_coaster

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

With no annotations, the description carries the burden and does meaningful work: free-tier quota (3/month vs unlimited Pro), a paid-feature gate on QR codes, automatic mesh decimation for oversized results, and the fact that a PNG preview is a floor rather than the full result. It stops short of saying whether the call is synchronous/expensive or what the returned payload contains.

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 core purpose is front-loaded, but the text is bloated by a pricing URL and upgrade pitch, and the inline 3D stage is explained twice (once in the opening paragraph, again in a dedicated INLINE 3D STAGE section). Ad copy and repetition dilute the operational content.

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 10-parameter, no-annotation, no-output-schema generation tool, the description must explain both the parameters and the result. It covers quota and the viewer but leaves all ten inputs opaque and says nothing about what the call returns beyond a preview/stage.

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 nominally 100%, but every property description is only a default value ("Default: \"\"", "Default: \"round\"") with no meaning. The description never explains top, bottom, photo_mask, brief_id, include_step, or allowed values for shape/material, so an agent still cannot tell what these fields do — the schema provides defaults, not semantics, and the prose does not compensate.

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 opening sentence states a specific verb and resource ("Generate a coaster with optional branding") and flags a conditional capability (QR code requires Kiln Business), which separates it from siblings like generate_keychain or generate_nameplate. It never explicitly names those siblings, so differentiation is implied by the product noun 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 useful routing context — design_session is not installed here, so compile_scad is the make→preview→iterate loop — but that is fallback routing rather than guidance on when to pick generate_coaster over the other ~40 generate_* product tools. Tier restrictions (3 free/month) are stated, which is a real usage condition.

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