Skip to main content
Glama
Cyan Eclipse Grantseal

Cyan Eclipse Grantseal

Official

grantseal_capture_use

Capture exercised scopes from a principal's own agent runtime and mint a diff verdict against the original sealed grant; reject captures from other provenance.

Instructions

Present an exercised-scope capture from the principal's own agent runtime (Class F records only) and mint the diff verdict against the original sealed grant. Captures from any other provenance are rejected. One metered op per use-window diff; UNVERIFIABLE captures do not meter.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "grant_seal_id": "<grant_seal_id>",
      "exercised_scopes": "<exercised_scopes>",
      "window_start": "<window_start>",
      "window_end": "<window_end>",
      "runtime_id": "<runtime_id>",
      "source": "<source>",
      "runtime_attestation": "<runtime_attestation>"
    },
    "name": "grantseal_capture_use"
  }
}

Input Schema

NameRequiredDescriptionDefault
sourceYes
runtime_idYes
window_endYes
window_startYes
grant_seal_idYes
exercised_scopesYes
capture_timestampNo
runtime_attestationYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior4/5

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

With no annotations, the description carries the burden and discloses real traits: provenance is validated and rejected otherwise, each use-window diff consumes one metered op, and UNVERIFIABLE captures are not metered. It omits permissions, idempotency, and what the minted verdict looks like, which keeps it short of full transparency.

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

Conciseness3/5

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

Three sentences, front-loaded with the main action, with no filler. However, undefined jargon like 'Class F records' and 'use-window diff' costs the reader more than the brevity saves.

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

Completeness2/5

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

For a write-like, metered tool with 8 undocumented parameters, no annotations, and no output schema, the description leaves both input contract and return value unexplained. The behavioral hints are useful but insufficient to invoke the tool confidently.

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

Parameters2/5

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

Schema description coverage is 0% across 8 parameters and 7 required fields, so the description must compensate. It only loosely gestures at grant_seal_id, exercised_scopes, runtime_id, runtime_attestation, and the window bounds; source, capture_timestamp, and the exact meaning/formats of the others are never explained.

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

Purpose4/5

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

States a specific action (present an exercised-scope capture, mint the diff verdict) against the original sealed grant, which distinguishes it from grantseal_get_verdict. The meaning is somewhat obscured by dense internal jargon ('Class F records', 'use-window diff'), but the verb and resource are identifiable.

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

Usage Guidelines3/5

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

Gives one concrete constraint for when this applies: only captures from the principal's own agent runtime are accepted, and other provenance is rejected. It does not name or contrast with siblings such as grantseal_check or grantseal_recompute, so the agent must infer the routing.

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