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

With annotations present, the description still adds meaningful context beyond them: a one-time link is emailed, the call merely triggers the message, only the participant can open the link, and the provider must be enabled. It also discloses the return shape. The phrase 'this just triggers the message' sits in mild tension with destructiveHint=true, though the emphasis on non-idempotent one-time links is consistent with idempotentHint=false.

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 core action, then behavior/limits, then return shape and targeting. Dense but each clause carries information; the em-dash asides are slightly heavy but not wasteful.

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 restating the return fields is a bonus rather than a gap. For a moderate-complexity mutation tool the description covers preconditions, behavior, identifier options, and campaign targeting; only edge behavior (repeat calls invalidating prior links, provider-not-enabled errors) is left implicit.

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 only 50%, so the description must compensate: it clarifies that participantId/participantEmail are alternative identifiers and explains campaignId targeting and fallback to GROWSURF_CAMPAIGN_ID. Provider values are left to the schema enum, and no format hints for IDs/emails are given.

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 (ask/request confirmation) and resource (payout destination for a given provider), and explains the two ways to identify the participant (ID or email). It is clearly distinguishable from the adjacent read-only sibling growsurf_get_participant_payout_destination, which retrieves rather than requests.

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 real preconditions: the provider must be enabled for the program, the tool only sends the message (it does not confirm on the participant's behalf), and the participant is the only one who can act on the link. It does not explicitly name alternative tools (e.g., checking the existing destination before requesting confirmation), so it stops short of full routing guidance.

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