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

Annotations already cover safety (not read-only, open-world, not idempotent, non-destructive), and the description adds real behavioral context on top: the required draft state, the fact that it can be safely re-invoked to resend, and the downstream dependency that businesses are only invited after the customer confirms. It does not state failure modes or delivery/auth requirements, keeping it short of a 5.

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 tight sentences, front-loaded with the action and its scope, followed by usage triggers and the downstream consequence. Nothing is redundant or padded.

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 two-parameter mutation with no output schema, the description conveys the state precondition, the resend use case, and the side effect on downstream business invitations. It stops short of describing what the agent should expect on success or the specific validation errors it may encounter.

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 100% and both parameters are fully documented in the schema, including the origin of each value (returned by create_request). The description adds only the implicit precondition that request_id must reference a valid draft request, which is a modest semantic addition.

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?

Names a specific verb (send/resend) and resource (the confirm email for a valid draft Bidit request), and the parenthetical '(or resend)' disambiguates the idempotent-ish behavior that the tool name 'submit_request' obscures. An agent can immediately tell this tool does not create or submit a request, it emails a confirmation.

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 two concrete triggering conditions: after fixing validation errors, and when the customer did not receive the email. It does not explicitly name a sibling alternative or state when NOT to use it (e.g. for already-confirmed requests), but the 'valid draft request' precondition implicitly excludes those cases.

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