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

Annotations only declare the mutation/safety profile; the description adds the real behavioral context: a 24-hour expiring link, output format defaults, template sample values used for any omitted field, empty arrays as the way to clear discounts/extra_lines/messages, logo replacement semantics, and the daily document quota. The returned fields and the 'notes for anything left out or cut' behavior are disclosed as well.

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 action, prerequisites and defaults are front-loaded in the first three sentences, and nearly every clause carries information. It is a single dense block that re-states some item fields already in the schema and would scan better with structure, but there is little pure filler.

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 nested generation tool this is close to complete: prerequisites, defaults, inheritance rules, logo constraints, output summary, quota and legal policy are all covered, and the output schema can carry return shapes. Only the unexplained layout-type parameters (sections, paper) leave a minor hole.

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?

Compensates strongly for the 47% schema coverage: items requires 1-200 entries with decimal-string prices ('4.50', never numbers), subtotal/tax/total are computed, and omitted fields inherit template samples. Gaps remain — paper, sections (which looks like layout/visibility control), tip, datetime, date_format and time_format are never explained in either the schema or the description.

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 artifact: make a receipt file from a template, rendered to png/jpeg/pdf with a 24-hour download link. It is clearly distinct from the listed siblings (list_templates supplies slugs, create_upload supplies logo file_ids) without the agent needing to open any 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?

Explicit ordering guidance: 'Call list_templates for a slug first', 'Set accept_terms to true', and 'resize a bigger one first' for oversized logos. It also names acceptable and prohibited use cases (lost receipt, bookkeeping, testing vs. refunds, expense claims, proof of purchase), so the agent knows when to decline.

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