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

Annotations only declare readOnlyHint=true; the description adds real behavioral context the annotations lack: an authentication prerequisite, the exact remediation path for Claude Code, and the non-obvious warning that start_login does NOT open this tool. That prevents a plausible but wrong recovery attempt.

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 is front-loaded in one sentence, with the access caveat clearly separated in its own block. Slightly verbose in the remediation instructions, but every line is actionable rather than filler.

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 one-parameter read tool with no output schema, the auth story is well covered, but the description says nothing about what a returned request contains or what happens on an unknown reference ID — a gap the absent output schema would otherwise have filled.

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 100% schema description coverage on a single parameter, the schema already documents reference_id. The description's parenthetical '(your unique identifier)' reinforces ownership but adds no format, source, or retrieval semantics beyond the schema.

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 ('Get a verification request') and pins the lookup key as the caller's own reference ID, which implicitly distinguishes it from id-based siblings like get_verification_request. However, it never names the sibling it is not, so an agent must infer the distinction.

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?

The ACCESS block gives a clear operating condition (requires a Proof account, authenticate first), which is genuinely useful context. But it says nothing about when to choose this tool over get_verification_request or list_verification_requests, leaving the retrieval-by-reference vs by-id decision to inference.

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