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

With no annotations, the description carries the load and does well: it discloses the hosted-page flow, that the signer signs in and types their name to e-sign, that agents cannot sign, and that the tool returns a link to hand over. It omits what happens on duplicate requests, whether prior links are invalidated, and any permission or rate limits.

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 action and the payoff (the signing link), then the kind branch, then the signer flow. The telegraphic 'kind contract:' / 'kind job_document:' fragments are efficient but slightly harder to parse than full sentences.

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?

An output schema exists, so return values need not be explained, and the description covers the branching logic, the signer experience, and the agent capability limit for a 9-parameter, annotation-free tool. An agent has enough to invoke it correctly without further reading.

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 67%, and the description adds real meaning beyond it: `text` must be the agreement exactly as the shop wrote it, and `kind`'s two values each map to a distinct input set and source. It leaves `job_id`, `customer_id`, and `signer_role` largely to the schema, which does document them, so this is close to adequate.

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 concrete verb and resource: ask someone to sign a document on a hosted page and return the signing link. It also splits the two operating modes (contract text vs. stored job PDF via documents.list), which lets an agent pick correctly. It does not, however, distinguish this from the closest sibling, signatures_newLink, so the agent may still hesitate between the two.

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?

Clear in-context guidance for choosing between `kind: contract` (shop-authored text, never written by Doing Work) and `kind: job_document` (a PDF from documents.list), plus the hard rule 'Agents can never sign.' No exclusions against signatures_newLink, signatures_get, or the requestSignOff siblings are given.

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