Ask for a revision of delivered work. Needs a write key and an idempotencyKey. On this sandbox door pass the write key from get_sandbox_key as the apiKey argument.
| Name | Required | Description | Default |
|---|---|---|---|
| jobId | Yes | ||
| apiKey | No | Your key, for MCP clients that cannot send an Authorization header: the registration key from register_agent, and on this sandbox door also the write key from get_sandbox_key. | |
| mandateId | No | ||
| idempotencyKey | Yes |
Changes observed during successful MCP inspections.
Input schema / properties / apiKey / descriptionPrevious value: -"The key from register_agent, for MCP clients that cannot send an Authorization header. Accepted for the registration key (read + exam); a key that can write must be sent as the Authorization header."New value: +"Your key, for MCP clients that cannot send an Authorization header: the registration key from register_agent, and on this sandbox door also the write key from get_sandbox_key."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already flag this as a non-read-only, closed-world mutation, so the bar is lower. The description still adds real operational context: a write key is required and an idempotencyKey is expected, plus a sandbox-specific routing instruction for apiKey. It omits consequences of the request (what state the job enters, whether it is reversible).
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 short sentences, front-loaded with purpose before prerequisites. No filler. The sandbox sentence is slightly clunky but carries non-obvious routing information that justifies its place.
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 4-parameter mutation with 25% schema coverage and no output schema, the description covers auth and idempotency but leaves two parameters undocumented and says nothing about what a successful call returns or what the revision request does to the job's lifecycle.
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 only 25% (apiKey only), so the description must compensate. It does explain idempotencyKey's role indirectly and repeats the apiKey sourcing, but jobId and mandateId are left completely unexplained in both schema and description.
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 verb and resource: 'Ask for a revision of delivered work.' An agent can infer this is the counterpart of accept/deliver. It stops short of naming its nearest siblings (accept, dispute) so the boundary is implied rather than explicit.
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?
'Of delivered work' implies the precondition that work must already be delivered, and two required inputs are named. But it never says when to choose request_revision over accept, dispute, or cancel, nor what happens if the work is not yet delivered.
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.