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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, but the description adds genuinely new behaviour: pure in-memory evaluation with no filesystem or network imports, fixed millimetre units, a bundled Atkinson font, and hard limits of 100 parts and 10 sheets. What it omits is how the rendered files are returned and what warnings/errors look like.

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?

Four short sentences, front-loaded with what is produced, then constraints, then the escalation path. No filler and no repetition of schema or annotation 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?

With no output schema, the description carries the return-value burden and only partly discharges it: it says output is one file per sheet with part sizes, layers and warnings, but not the response shape (inline SVG/DXF text vs. references) or error/warning reporting. For a 9-parameter render tool that is a meaningful remaining gap.

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 only 22% across 9 parameters, so the description needs to compensate. It clarifies units for the numeric geometry inputs ("Uses millimetres") and that libraries are virtual rather than fetched, but says nothing about gap, kerf, margin, layout or params, leaving most parameters undocumented in both places.

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 ("Render .kerf source") plus concrete outputs (SVG or DXF, one file per sheet) and included metadata (part sizes, layers, warnings). It is clearly distinguishable from the docs/examples/parameters siblings, though it never names them explicitly.

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?

"For production generators install @mylasertools/kerfscript locally" gives one real routing signal, and the 100-part/10-sheet bound tells the agent when the tool will refuse work. However there is no explicit statement of when to pick this over kerfscript_docs, kerfscript_examples or kerfscript_parameters, so the usage guidance is implied rather than stated.

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