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

Goes well beyond the readOnly/idempotent/non-destructive annotations by disclosing the trust model: pure client-safe compute, zero network, plaintext never required, and the exact failure semantics of each result class (proof-only, disclosed-verified, commitment-only, failed). The commitment-only caveat ('structural + plaintext-exclusion only') is a genuinely important behavioral warning.

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 the first clause, and nearly every clause carries operational information (pointer semantics, scheme check, proof cross-binding, disclosure path, result taxonomy). It is a dense single block with spec reference noise, which costs a point, but nothing is truly redundant.

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?

No output schema exists, yet the description enumerates the per-entry {pointer, verifiable} result states, which is the essential return contract. It stops short of stating that the tool needs either a full artifact or the component fields (0 required params), a minor selection gap for a 6-parameter tool.

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 coverage is 100% and already notes artifact-vs-components alternatives, but the description adds real meaning: the disclosure object is a {pointer, salt, input_value} authorized-verifier package and the recomputation formula is sha256(salt || cgCanon(input_value)). That explains what the otherwise-undocumented disclosure fields are for and what a 'verified' result means.

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 (verify) plus resource (private_inputs[] commitments) and the exact spec clause (§25 ocg-private-input@1). The differentiating constraint -- verification without plaintext witness -- is stated up front, so an agent can distinguish this from sibling validators like verify_input_attestations or validate_private_inputs-style checks.

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?

Tells the agent when each mode applies: proof present vs. absent, and when the optional disclosure package is used (authorized-verifier path). It does not name a sibling tool as the alternative for the proof-only case, which keeps it below 5, but the conditions are explicit enough to select correctly.

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