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

With no annotations, the description carries the full burden and does well: it discloses the outbound email, the 24-hour TTL, and single-use semantics, which are exactly the traits an agent cannot infer. Gaps remain on permissions required, behavior when a request is already pending, and what the call itself returns (e.g., a request id to correlate polling).

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?

Two short sentences, zero filler, with the action and its constraints front-loaded before the follow-up instruction. Every clause earns its place.

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?

The description is complete on the side-effect and lifecycle (email, TTL, single use, polling), which is the hard part for an unannotated tool. But with no output schema and low parameter coverage, an agent still cannot tell what the call returns, how failures are surfaced, or what the optional parameters do — so it is adequate rather than complete.

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 only 33% — just idempotency_key is documented — and the description adds nothing about `note` (the message shown to the owner) or `callback_url` (where a result is posted). With two of three parameters undocumented in both places, the description fails to compensate for the coverage gap.

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 and resource ('Email the account owner a one-tap Approve link') plus mechanism-level detail: 24-hour expiry, single use. It is distinguishable from siblings like start_email_verification or get_verification without opening any 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 concrete sequencing guidance — 'Poll get_verification until verified or denied' — which tells the agent what to do after the call. However, it never states the conditions that select this tool over alternatives (e.g., when an approval escalation is warranted vs. direct verification flows) or any prerequisites.

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