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

Annotations only broadly signal readOnly=false, idempotent=false, and destructive=false. The description adds substantial behavioral context: records live in process memory, can be refreshed or evicted, are neither durable nor append-only, valid proofs may be published to Nostr, rate limits are shared across /mcp, and no deletion endpoint exists. It also clarifies error semantics and that publication failure is surfaced through attestationStatus.

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?

The description is long but organized into labeled sections (PURPOSE, USAGE, PARAMETERS, BEHAVIOR, RETURNS, ERRORS), making it skimmable and front-loaded with purpose. Each section provides operationally relevant information for a complex tool, and there is no filler or redundant prose.

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 tool with nested parameters, side effects, external publication, lifecycle behavior, and multiple error modes, the description covers everything an agent needs: usage boundary, parameter shapes, invariants, return fields, error codes, rate limits, and payment requirements. Combined with the rich schema and annotations, nothing essential is missing.

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 the schema already documents proof structure, the five-signal ordering, and the snapshotDigest equivalence constraint. The description summarizes these constraints clearly, but it does not add meaning beyond what the schema already provides. Per the high-coverage baseline, 3 is appropriate.

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 action set: verifies Groth16/BN254 coordinates, indexes them through a lifecycle, and attempts Nostr NIP-78 publication. It clearly differentiates from proof.verify by naming the sibling in the usage section, so an agent can distinguish submission from pure validation without inspecting the 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?

The USAGE section explicitly says when to use this tool ('submit proof coordinates for lifecycle lookup and optional Nostr publication') and when not to ('Do NOT use when only validating an encoded proof against telemetry data; use proof.verify instead'). This is direct alternatives-and-exclusions guidance with nothing left to inference.

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