link_account

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

Adds real context beyond the annotations: it states the write flag requirement, warns 'Not live-validated', and flags that initiator token issuance/merge semantics are unverified — exactly the kind of caveat an agent needs before a destructive write. It stays consistent with destructiveHint=true and idempotentHint=false, though it never says what state is overwritten or what a merge does.

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 the endpoint and mutating/write-flag status, then adds caveats — every sentence carries signal. The closing 'merge semantics remain unverified' is slightly terse/cryptic, but it is not padding.

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; the description instead covers the risky parts — mutability, required write flag, auth model, validation status. The main residual gap is that it never explains how confirm_destructive should be used on this destructive call.

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?

With 0% schema coverage across 4 params, the description does useful work: it explicitly negates the path parameter and points payload at get_schema('UserLinkRequestProto'), and explains the body token's role. It says nothing about 'query' or, more importantly, 'confirm_destructive', which is a notable omission for a destructive operation.

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+resource ('link_account') and pins it to a concrete endpoint (POST /v1/user/link), plus clarifies the auth/approval-token mechanic. It does not differentiate from nearby siblings like accept_friend_invite or register_anonymous_user, so an agent still has to infer the boundary.

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 a hard precondition (FLIGHTY_ALLOW_WRITES=true) and distinguishes the approving account from the body token, which is genuine usage context. However, it never says when to prefer this over sibling flows such as accept_friend_invite or sync_account, and offers no exclusions.

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