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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false; the description earns credit beyond them by disclosing the $0.001 per-call cost, that failures are free, the validation rule that every role needs a signature field, and that re-saving a name overwrites it. It does not say what is returned (template id) or whether deletion/replacement is recoverable.

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 purpose and mechanism, and the follow-up sentences about role ordering and name replacement are useful. The cost is stated twice ('$0.001. Costs $0.001 per call'), which is wasted text in an otherwise tight description.

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 mutation tool with no output schema and 8 parameters, the description covers pricing, failure behavior, coordinate conventions, validation constraints, and overwrite semantics. The main remaining gap is the response shape (template identifier) and any preconditions on the source PDF, which an agent would want before calling.

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?

At 63% schema coverage the schema carries much of the burden, but the description adds genuine meaning: roles are signers 'in order', field coordinates are percentages of the page consistent with esign_send, and every role must carry a signature field. It leaves 'order' (parallel vs sequential), 'message', and 'expires_in_days' unexplained, so not a 5.

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 ('Save a PDF from the file store ... as a template') and pins down the differentiator: fields are placed once per signer role so later sends don't need re-placement. That separates it from esign_send (one-off send) and esign_send_template (reuse), which are its nearest siblings.

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 use case clearly ('contracts, NDAs and waivers go out later without placing a field again') and implicitly contrasts with esign_send by referencing it for coordinate semantics. It also states the replacement rule for reusing a name. It stops short of an explicit 'use X instead when...' exclusion, so a 4 rather than a 5.

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