Check a sha256 against the live public-root merkle via GET /api/proof?sha=. Three states only: VALID (included), INVALID (not a leaf), UNCHECKABLE (proof endpoint unreachable). Does not claim Ed25519 unless sig_ed25519 is present and checked separately. Never a grade.
| Name | Required | Description | Default |
|---|---|---|---|
| sha256 | Yes | 64-char hex digest to test for inclusion. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of disclosing behavior, and it does so thoroughly. It names the HTTP endpoint, defines the three possible outcomes, flags the unreachable-endpoint case, and explicitly warns against overclaiming Ed25519 or grading, which are important behavioral caveats.
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?
Three tightly packed sentences convey the endpoint, input, output states, and important exclusions with no filler. The most important action and endpoint are front-loaded, and every sentence adds distinct value.
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?
Given a simple one-parameter schema, no output schema, and no annotations, the description is fully self-sufficient. It covers what the tool does, how it behaves on unreachable endpoints, what it does not verify, and what the possible return states are, which is all an agent needs to invoke it correctly.
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 single parameter sha256 is already documented as a 64-char hex digest. The description reinforces that this value is checked against the merkle proof endpoint, but it does not add substantial meaning beyond what the schema already states.
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 verb ('Check'), a specific resource (sha256 against the live public-root merkle), and the exact retrieval path (GET /api/proof?sha=). It also enumerates the three distinct result states, making the tool's function unmistakable and distinct from siblings like get_root or verify_card.
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 clearly indicates what this tool is for and what it is not for: it only checks merkle inclusion, never produces a grade, and does not assert Ed25519 validity unless separately checked. It provides useful when-not-to-use guidance, though it does not explicitly name alternative sibling tools.
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.
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.
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.
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.
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.