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

Annotations only declare the generic profile (not read-only, open-world, not idempotent); the description adds real behavioral substance the annotations cannot: signers are emailed immediately, parallel vs sequential ordering, per-signer links and browser signing, signed PDF plus certificate returned to everyone, and the exact event names emitted. It even discloses cost ($0.20 per call, nothing on failure), which is a rare and highly actionable detail.

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?

Front-loaded with the core action, then layered into sourcing, signing mechanics, field placement, ordering, and events. Nearly every sentence carries operational information; the base64 warning is a worthwhile guardrail, though the paragraph is dense enough that an agent must read the whole block to extract the field-placement rules.

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 usefully substitutes event names for return-value knowledge and covers cost and failure behavior. It stops short on a few things an agent would want: what identifier the call returns, the expires_in_days default/max, and any pointer to esign_cancel or esign_remind for follow-up.

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 43%, so the description must carry weight and it does: it explains the fields array coordinate system (percent from top-left), supplies a sizing heuristic ('30 x 5 fits a line'), and states the hard rule that every signer needs a signature field. The generated-signature-page behavior when fields is omitted is likewise explained. Minor params (expires_in_days, message, title) are left to the schema.

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?

Opens with a specific verb, resource, and scope: send a PDF from the file store to up to 10 people to sign. An agent immediately knows this is the ad-hoc send path rather than the template path, though the sibling esign_send_template is never named, so the differentiation is inferred from 'from the file store' 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?

Gives concrete when-to-use guidance, including how the file gets into the store (files_upload_link page_url or documents_create_pdf) and an explicit when-not ('Never type a PDF out as base64'). It also routes event consumption to account_events or notify_subscribe. The one gap is that it never states when to prefer esign_send_template over this tool.

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