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

Annotations already declare readOnlyHint=true, so the safety profile is covered; the description adds the non-obvious auth gating, the retry-after-authenticate flow, and that results are paginated. That is real behavioral value beyond the annotations, though response shape and default page size remain unstated.

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 front-load what the tool does and what it returns, followed by a compact, actionable access note. Nothing is padded, though the second sentence about pagination could merge with the first.

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 correctly compensates by noting paginated results, and the auth prerequisite is the single most important missing piece from structured data — it is present. Filter semantics live in the schema, so nothing critical is absent; default limit/ordering remain unspecified but are minor.

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% and all four parameters (page, limit, status, reference_id) are documented in the schema, including the non-obvious 'active' semantics. The description only says 'optional filters', adding nothing the schema does not already carry, 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?

The description states a specific verb and resource ('List verification requests') plus the filtering and pagination behavior, which is enough to distinguish it from mutation siblings like cancel_verification_request or create_verification_request. It does not, however, distinguish itself from the closely named read siblings get_verification_request and list_verifications.

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 tells the agent the prerequisite (a Proof account) and the exact recovery step (authenticate, then retry), and it explicitly warns that 'start_login does NOT open this tool' even though start_login exists as a sibling — a genuine when-not instruction. It stops short of stating when to prefer this over get_verification_request or list_verifications.

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