wait_for_request

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

Beyond readOnlyHint=true it discloses the polling mechanics (2s initial, 1.5x backoff, 30s cap, jitter), the terminal-state set, and the auth/restart gating requirement. It omits return shape and whether polling consumes quota, but the operational profile is well beyond what the annotation conveys.

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?

Purpose and termination conditions are front-loaded in the first sentence, with polling mechanics immediately after. The ACCESS block is a little ceremonious but carries a genuine gating constraint, so it earns its space.

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?

With no output schema, the description carries return-semantics burden and does enumerate the terminal states an agent will observe on completion, plus the timeout->pending path documented in the schema. It stops short of describing the full response shape or failure modes.

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 100%: 'id' and 'timeout_seconds' are both fully documented in the schema, including the client-timeout caveat and re-call behavior. The description adds no parameter detail, so the baseline 3 applies.

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 (poll/wait) and a precise resource (verification request), and enumerates the terminal states (completed, expired, cancelled). The resource naming distinguishes it from the nearby wait_for_verification sibling, which targets verifications 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 clear blocking semantics and an explicit precondition (Proof account + PROOF_API_KEY) plus a negative rule ('start_login does NOT open this tool'). It does not, however, contrast this blocking poll against the non-blocking get_verification_request, so the agent must infer when to block versus check once.

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