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

Beyond the annotations, the description discloses that `fields` is a whole-list replace, that the operation only applies to unsent drafts, that no credits or invites are involved, and that a Bearer token is required. This is exactly the kind of behavioral detail an agent needs beyond readOnly/idempotent/destructive hints.

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?

Three terse sentences deliver scope, field semantics, exclusions, and auth requirements with no filler. The most important information is front-loaded.

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?

Given the output schema exists and annotations cover idempotency and read-only behavior, the description provides all necessary operational context: when it is valid, what fields look like, replacement semantics, exclusions, and auth. Nothing critical is missing.

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 0%, but the description compensates by detailing the expected `fields` item shape: `{type, party, name?, required, position: {page_number, x, y, width, height}}`. It also clarifies that `fields` is a whole-list replace. The `document_id` parameter is not elaborated, but its meaning is inferable from the draft context.

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?

The description opens with 'Replace the fields on an unsent Draft,' which clearly identifies the verb, resource, and scope. It also distinguishes itself from siblings by explicitly stating 'No credit debit, no invites,' so an agent knows this is not a billing or invitation operation.

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?

The description says this applies to an 'unsent Draft' and excludes credit/invite operations, giving useful context for when to use it. It does not explicitly name an alternative like send_draft for sending, but the boundary is clear enough from the wording.

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