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

Annotations only declare readOnly/destructive/openWorld hints, so the description carries most of the behavioral burden and delivers: it names the emitted artifacts (invitation/reminder email, signed callback) and returns the created object shape, which compensates for the absent output schema. It stops short of covering permissions or quota edge cases beyond the cost note on 'email' delivery.

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-loads identity and scope, then usage, then prerequisite, then return shape, then lifecycle siblings. Every sentence carries distinct routing or behavioral information with no filler despite the tool's complexity.

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 16-param mutation tool with no output schema, the description supplies what is otherwise missing: the return fields ({ id, status, url, deliveryStatus, expiresAt, next }), the prerequisite call, and the tracking/withdrawal siblings. Nothing an agent needs to invoke it correctly is absent.

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 description coverage is 100% (baseline 3), and the description adds cross-parameter semantics the schema cannot: prefill/context/readonly all key off fields_list keys, and the fields_list call is a hard prerequisite. Most individual parameter meaning still lives in the schema, so it is a modest bump over baseline.

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 precise verb and resource and immediately scopes it: 'one assignment of a published form to one named recipient, with its own link, prefilled answers, expiry and optional callback.' It explicitly contrasts with the sibling formShareLink_create ('for a link anyone may fill'), so an agent can pick between them 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 when-to-use condition ('answers from a specific person and want to know whether they answered'), names the alternative and its selection condition, and adds a required prerequisite ('Call fields_list(formId) first'). It also routes follow-up work to request_get, request_cancel and load_skill('requests').

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