Privately request a missing model, format or capability. First call previews; repeat the same wanted/task with confirm_token to submit. No delivery promise.
| Name | Required | Description | Default |
|---|---|---|---|
| task | Yes | ||
| wanted | Yes | ||
| confirm_token | No | From the preview; wanted and task must match. |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
Input schema / additionalPropertiesRemoved value: -falseInput schema / properties / confirm_token / descriptionPrevious value: -"Token from the preview; wanted and task must match exactly before expiry."New value: +"From the preview; wanted and task must match."Input schema / properties / confirm_token / maxLengthRemoved value: -2048Input schema / properties / confirm_token / minLengthRemoved value: -1Input schema / properties / task / maxLengthRemoved value: -1000Input schema / properties / task / minLengthRemoved value: -1Input schema / properties / wanted / maxLengthRemoved value: -500Input schema / properties / wanted / minLengthRemoved value: -1Output schema / additionalPropertiesRemoved value: -trueInput schema / properties / confirm_token / descriptionPrevious value: -"Return the first call token with the exact same wanted and task to explicitly submit before expiry."New value: +"Token from the preview; wanted and task must match exactly before expiry."Input schema / properties / task / descriptionRemoved value: -"The job you were doing for your user when you needed it."Input schema / properties / wanted / descriptionRemoved value: -"What you were looking for (a model, dataset, tool, file, format, capability...)."Input schema / properties / confirm_tokenAdded value: +{
+ "description": "Return the first call token with the exact same wanted and task to explicitly submit before expiry.",
+ "maxLength": 2048,
+ "minLength": 1,
+ "type": "string"
+}Output schema / (root)Previous value: -nullNew value: +{
+ "additionalProperties": true,
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only tell the agent this is a non-read-only, non-destructive, closed-world write; the description adds real context beyond that: the request is private, it is two-phase with a preview gate, and 'No delivery promise' sets an explicit expectation about outcome. It stops short of describing what the preview returns or whether duplicate requests are merged.
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, each carrying distinct information (what, how, caveat), with the core purpose front-loaded and zero filler.
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 3-parameter tool with an output schema and non-destructive annotations, the description covers purpose, the two-call flow, privacy and the no-guarantee caveat. The only material omission is the meaning of the required 'task' parameter.
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 only 33%: only confirm_token is documented ('From the preview; wanted and task must match'). The description implies what 'wanted' holds (the missing model/format/capability) but leaves 'task' completely undefined, which is a significant gap for a required parameter.
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?
Specific verb and resource: 'request a missing model, format or capability'. An agent can tell what is being asked for, but the description never contrasts this with the closely-named sibling request_feature, so the boundary between the two is left to inference.
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?
It clearly explains the two-step invocation protocol (preview first, then repeat with confirm_token), which is genuine procedural guidance. However, it says nothing about when to choose this over request_feature or request_crawl_access, nor about prerequisites such as auth or quota.
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.