Skip to main content
Glama

Council of AI GSPC

by io.github.CSOAI-ORG

verify_card

Verify a signed gspc.measurement-card under the published rule (https://councilof.ai/signed/HOW-TO-VERIFY.md): recompute the id from the canonical body bytes, then check the Ed25519 signature under the PINNED key published at did:web:csoai.org#card-attestation-1. A card that carries its own key proves only that the file is self-consistent — anyone can alter a body and sign it with a key they just generated — so a signer other than the published key is reported INVALID. Three verdicts, never two: VALID, INVALID (with the reason), or UNCHECKABLE when the check could not be completed — 'could not check' is a different claim from 'forged'. Accepts the card as a JSON object, a JSON string, or a councilof.ai / csoai.org URL. Never a certification.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cardYesThe signed card: an object, a JSON string, or a councilof.ai / csoai.org URL to one.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations provided, the description carries the full burden, and it delivers: it discloses the verification algorithm, the pinned key source, why self-carried keys are treated as INVALID, the exact three-verdict model, and the distinction between 'could not check' and 'forged'. This is far more transparent than a typical one-line tool description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is longer than average but every sentence earns its place: rule link, key ownership, signing caveat, verdict set, input formats, and certification exclusion. It is front-loaded with the core action and resource, and the additional detail is dense rather than padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations and no output schema, the description is unusually complete: it defines the input forms, the acceptance rule, the exact verdicts, and the failure semantics. The only minor gap is that it does not specify the exact output envelope or field names for the verdict result, though the verdict vocabulary itself is clear.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for the single parameter, so the baseline is 3. The description adds meaningful semantics: the card must be signed, a self-provided key is not sufficient, and the input can be a JSON object, JSON string, or councilof.ai/csoai.org URL. It reinforces the schema without introducing conflicts.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Verify a signed gspc.measurement-card' under a published rule. It goes further by naming the exact mechanism (recompute id, check Ed25519 signature under the pinned key), which distinguishes it from siblings like verify_inclusion.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context for when this tool is appropriate: verifying a signed measurement-card under a specific published rule. It explicitly excludes certifications ('Never a certification'), but it does not name sibling alternatives or state when not to use it beyond that single exclusion.

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

All Council of AI GSPC toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0
Disambiguation4/5

Each tool has a distinct target resource or action, but some boundaries require careful reading: get_card, verify_card, and verify_inclusion all deal with cards/proofs, while art50_marking_evidence and rwa_evidence are both paid evidence packs. The detailed descriptions help separate them, so misselection is unlikely but not impossible.

Naming Consistency3/5

There are clear verb-prefixed clusters like get_axis/get_card/get_root and verify_card/verify_inclusion, but several tools use bare noun phrases: board_totals, commission_card, receipts_batch, rwa_evidence, and art50_marking_evidence. The naming is readable and snake_case throughout, but the verb/noun convention is mixed.

Tool Count5/5

With 11 tools, the set is well-scoped for a GSPC board, measurement-card, evidence, and verification server. Each tool serves a distinct endpoint or workflow, and none feels redundant or purely decorative.

Completeness4/5

The surface covers board totals, axis details, roots, card retrieval, verification, paid evidence, and historical receipts. A minor gap is the absence of a list_axes tool to enumerate all board axes or a direct get_measurement_card endpoint, but existing tools can work around this via list_cards and verify_card.

Resources