warp-agent-mcp

Report a Problem to Warp

report_issue

Idempotent

Report a problem with Warp's tools to the Warp team. Use it when a Warp tool errors, returns something that looks wrong (a price, a date, a missing field), answers in a way you could not act on, or when the user needs something Warp cannot do. Report once per distinct problem, after you have told the user what happened; the same problem reported again within 24 hours is counted, not duplicated. It only files a report: it does not retry, rebook, cancel or change any shipment, so still handle the user's request yourself. Describe the problem in your own words. Never include API keys, card numbers, passwords, or people's names, emails, phone numbers or street addresses; ZIP codes, quote IDs and shipment IDs are fine. Requires a connected Warp account.

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": {
      "category": "<category>",
      "tool_name": "<tool_name>",
      "summary": "<summary>",
      "expected_behavior": "<expected_behavior>",
      "observed_behavior": "<observed_behavior>",
      "customer_blocked": "<customer_blocked>"
    },
    "name": "report_issue"
  }
}

Input Schema

Name	Required	Description
`summary`	Yes	One line: what went wrong
`category`	Yes	tool_error: a tool failed or returned an error. unexpected_result: it worked but the result looks wrong. confusing_response: you could not tell what to do with the response. missing_capability: the user needed something no Warp tool does.
`quote_id`	No	Quote ID involved, if any
`tool_name`	Yes	The Warp tool involved, e.g. ltl_quote or book. Use the closest tool for missing_capability.
`error_code`	No	Error code returned by the tool, e.g. UPSTREAM_ERROR
`request_id`	No	Request ID from an error response, if any
`occurred_at`	No	When it happened, ISO 8601. Defaults to now.
`shipment_id`	No	Shipment ID involved, if any
`customer_blocked`	Yes	true if the user could not finish what they were trying to do
`expected_behavior`	Yes	What you or the user expected to happen
`observed_behavior`	Yes	What actually happened, including any error code or message returned

Schema Changelog

Changes observed during successful MCP inspections.

Changed8 schema fields changedOct 29, 2026
- removedInput schema / properties / request_id / $ref
```
Removed value: -"#/properties/quote_id"
```
- addedInput schema / properties / request_id / maxLength
```
Added value: +120
```
- addedInput schema / properties / request_id / pattern
```
Added value: +"^[A-Za-z0-9._:\\-]+$"
```
- addedInput schema / properties / request_id / type
```
Added value: +"string"
```
- removedInput schema / properties / shipment_id / $ref
```
Removed value: -"#/properties/quote_id"
```
- addedInput schema / properties / shipment_id / maxLength
```
Added value: +120
```
- addedInput schema / properties / shipment_id / pattern
```
Added value: +"^[A-Za-z0-9._:\\-]+$"
```
- addedInput schema / properties / shipment_id / type
```
Added value: +"string"
```
AddedOct 1, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well beyond the annotations by explaining that the tool is non-remediating (no retry, rebook, cancel, or change) and must be paired with the agent still resolving the request. It adds a deduplication policy ('report once per distinct problem; the same problem reported again within 24 hours is counted, not duplicated'), a data-handling policy listing forbidden PII versus permitted identifiers, and an auth prerequisite ('Requires a connected Warp account'). These are behaviors an agent could not infer from readOnlyHint=false and idempotentHint=true alone.

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

Conciseness4/5

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

Front-loaded with purpose then triggers, with the non-action caveat and privacy rules following in logical order; nearly every sentence carries distinct operational value. It is dense single-paragraph prose for a tool with this much nuance, so length is justified, though a slightly tighter structure would read faster.

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

Completeness5/5

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

For an 11-parameter, 6-required tool with no output schema, the description covers the gaps that matter: when to file, what counts as one problem, privacy constraints on the free-text fields, the account prerequisite, and the fact that filing does not resolve the user's request. Nothing an agent needs in order to call it correctly is missing.

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

Parameters3/5

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

Schema description coverage is 100%, including a documented enum for category and patterns for IDs, so the schema carries most of the burden and baseline 3 applies. The description does add real guidance on content: 'Describe the problem in your own words' plus explicit rules on what may and may not appear in free-text fields (ZIP codes, quote IDs, shipment IDs allowed; names, emails, phones, addresses forbidden).

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

Purpose5/5

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

States a specific verb and resource ('Report a problem with Warp's tools to the Warp team') that is unmistakable against a sibling set dominated by quoting and booking tools. The description also clarifies it is a feedback channel, not a shipment action, so there is no ambiguity with tools like status or track.

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

Usage Guidelines5/5

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

Enumerates concrete trigger conditions: a tool errors, returns something that looks wrong (price, date, missing field), answers in a way the agent could not act on, or the user needs something Warp cannot do. It also gives a sequencing rule ('after you have told the user what happened') and an exclusions rule ('it only files a report: it does not retry, rebook, cancel or change any shipment, so still handle the user's request yourself'), which routes the agent away from using it as a fix-it tool.

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

All warp-agent-mcp tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.