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

Annotations already cover safety and idempotency, and the description adds real value beyond them: per-request cost, that each send produces emails, signing links, and a signed PDF with certificate, plus the 50-set cap. It loses a point for repeating the pricing sentence nearly verbatim and for the opaque clause 'nothing if none are found', which does not say what would not be found.

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 and mostly dense, but the pricing appears twice in adjacent sentences ('$0.20 per request sent. Costs $0.20 per request sent...'), which is pure waste in a four-sentence description. The trailing 'nothing if none are found' clause is ambiguous enough to add confusion rather than signal.

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 story by naming emails, links, and the signed PDF with certificate. Missing pieces are modest but real: no mention of expiry behavior, signer-count limits per role, or what happens if a template is not found (the ambiguous 'none are found' hints at it without resolving it).

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?

With 67% schema coverage it usefully explains the un-inlined `signers` parameter — one signer per template role, in the template's order — and clarifies that each entry in `sets` is one request's signer list. It does not touch `expires_in_days`, which has no schema description either, so that parameter remains undocumented end to end.

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 ('Send a saved template to new signers') and immediately scopes the two modes: one request via signers, or up to 50 batched requests via sets. It explicitly relates itself to esign_send, so an agent can place it 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 concrete case for the batch mode ('the same NDA to every new contractor') and distinguishes single vs. multi-request sends. It stops short of an explicit exclusion against siblings like esign_send or esign_signing_link — it only says behavior is the same, not which to pick when.

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