verify_evidence_packVerify a review pack receipt by receipt. Each verdict comes from the signed envelope itself, never from stored state, and results are per-receipt, never an average.
| Name | Required | Description | Default |
|---|---|---|---|
| pack | No | A pack object, or "sample" for the published sample pack. | |
| public_key | No | Key to pin every receipt against. Omit to use each envelope's embedded key. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already provide readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavior: each verdict is derived from the signed envelope itself, never from stored state, and never averaged across receipts. This goes beyond the structured annotations and helps the agent understand the verification semantics.
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 two sentences and wastes no words. The most important operational constraint, per-receipt results sourced from the envelope, is compactly stated. It is dense but readable.
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 read-only tool with only two parameters, no output schema, and a fully described input schema, the description gives sufficient context for most calling decisions: pack scope, per-receipt outputs, and independence from stored state. It could further explain how results are returned, but no output schema makes that less critical.
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 both parameters already have clear descriptions in the schema. The description does not materially add parameter-level semantics beyond what the schema provides, so the baseline score of 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 clearly identifies the verb and resource: verify an entire pack, receipt by receipt. The per-receipt qualifier distinguishes it from receiving a single aggregate result, and the scope is implied to differ from verify_receipt. Minor inconsistency: title says 'evidence pack' while the description says 'review pack'.
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 description makes it clear that this tool verifies a whole pack and that results are per-receipt, which implies use for pack-level verification rather than single-receipt verification. However, it does not explicitly name verify_receipt as the alternative for individual receipts, nor does it state exclusions or conditions for choosing one over the other.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have clear distinct jobs: decode, verify, get, list, summarize. The only mildly overlapping pairs are decode_receipt vs explain_attestation_format and verify_receipt vs verify_evidence_pack, but the scopes are well described.
The dominant pattern is verb_noun: decode_receipt, get_public_key, list_my_receipts, verify_receipt. workspace_summary breaks the pattern by being noun-only, but the rest are consistent enough to be predictable.
10 tools is well within the ideal range for a focused attestation and receipt-verification server. Each tool serves a distinct operation from fetching samples and keys to decoding, verifying, listing, and summarizing receipts.
The read/verify workflow is well covered: format explanation, decoding, single-receipt verification, pack verification, sample artifacts, workspace listing, and summary. The main gap is that transparency proofs can be retrieved but there is no corresponding tool for independently verifying a transparency proof.