Every part is sent and I want the Court to hold the sealed record. Checks every declared part is in and holds the record sealed under the operator’s key, as POST /api/v1/notarise/held does; the Court holds no key that opens it. Closing an upload already closed is answered, not repeated. Credential: key. Cost: Free. Source: PD8 §10 (v1.3).
| Name | Required | Description | Default |
|---|---|---|---|
| uploadId | Yes | the upload id begin_held_upload returned |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden and does so well. It discloses validation of declared parts, operator-key sealing, the Court holding no opening key, idempotent handling of closed uploads, credential requirement, cost, and endpoint mapping.
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?
Front-loads the purpose and key constraints, and the credential/cost/source details are useful. However, the first sentence duplicates the second sentence's 'every part sent/declared part in' idea, slightly reducing conciseness.
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?
The description covers prerequisites, credential, key custody, idempotency, and cost, which is strong for a finalize operation. With no output schema, it does not describe the success response or returned sealed record, leaving that as the main contextual gap.
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 coverage is 100% and the sole uploadId parameter is fully documented in the schema as the UUID returned by begin_held_upload. The description adds no parameter-specific format or meaning beyond that baseline.
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 action: checks every declared part is in and holds the record sealed under the operator's key. It distinguishes finalization from part-upload and begin siblings by describing the closing behavior, though the opening user-voice sentence is slightly redundant.
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?
Implies the precondition 'Every part is sent' and notes that closing an already-closed upload is answered rather than repeated. It does not explicitly name sibling alternatives or add further when-not-to-use guidance, so it falls short of full routing instructions.
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.