POPCORN Witness Verifier

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

Annotations already cover readOnly/idempotent/non-destructive/closed-world, so the bar is lower, yet the description adds substantial non-obvious behavior: a privacy constraint (never send private payload bytes), a critical trust caveat (caller-supplied keys do not establish issuer identity), and explicit limitation boundaries. These are exactly the traits an agent needs and cannot get from the annotations.

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?

Five tight sentences, front-loaded with the core action and inputs, then privacy, trust, and limitation caveats in descending priority. No filler; every sentence adds an actionable or safety-relevant fact.

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 complex, recursive-schema tool with no output schema, the description covers the trust model and security constraints well. It is thin on how the chained previous_receipt and node/clock parameters factor into verification, and never characterizes the verification result, which a caller would want given no output schema.

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 0% across 7 parameters, so the description must carry the burden. It adds real meaning for the digest (caller-computed SHA-256), the nonce, and jwks (issuer trust anchor), but leaves expected_node_id, the recursive previous_receipt chain, and max_clock_accuracy_radius_ms entirely unexplained in both schema and description. Partial compensation only.

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) and resource (a POPCORN-WITNESS/2.0 receipt) plus the exact inputs the verification is performed against (caller-computed SHA-256 digest, nonce, trusted issuer keys). No siblings exist to confuse it with, and the scope is unambiguous. Minor title/description naming drift (TAIN 2.0 vs POPCORN-WITNESS/2.0) does not obscure the purpose.

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 negative scope that functions as when-not guidance: it does not prove on-chain settlement, establish current time, or grant authority, and caller-supplied keys do not establish issuer identity. Also tells the caller to send only the digest, never private payload bytes. It stops short of an explicit 'use this when you need X' routing statement, but with no siblings there is nothing to route between.

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