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

Annotations only declare the generic profile (not read-only, not idempotent, not destructive), but the description adds real behavior: the returned link expires in one hour, the call consumes one die download against the space's plan quota, and Free plans error out. Only the non-idempotent/one-download-per-call cost is hinted at rather than stated plainly, but the quota and expiry disclosure is exactly the value annotations cannot carry.

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?

Purpose and deliverables are front-loaded in the first sentence; nothing is filler. The final parenthesis chains three separate caveats (quota, Free plan, PDF/SVG routing) into one run-on clause, which costs some readability.

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?

With eight optional parameters and no output schema, the description correctly covers the return value (hour-limited download link) and the code-or-type requirement. It does not say what happens if no dimensions are supplied, despite all three size params being optional — the one remaining ambiguity for a zero-required-parameter tool.

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 63%, and the description fills the biggest gaps: length/width/height are the *inside* size in mm (the schema has bare numeric bounds with no description), and it explains what DXF vs CF2 mean ('for CAD and cutting tables' vs 'for die-makers, ArtiosCAD'). It also clarifies that format 'pdf' is really counted as get_dieline's call, which the enum alone does not convey.

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 ('Draw a production dieline ... at an exact size') plus the concrete outputs (DXF/CF2 download link). It explicitly separates itself from get_dieline, which handles the PDF/SVG die, so an agent can pick the right tool without opening a 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?

Gives the input prerequisites (a FEFCO/ECMA code or a type id from list_dielines) and names the alternative tool for the PDF/SVG case. It also flags the plan gate — Free spaces have no downloads, 'then it says so' — which tells the agent when the call will fail.

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