Fixter

Fix Issue

fix_issue

DestructiveIdempotent

Open a draft pull request that fixes one issue of the caller's account, on the customer's own repository. The order that works: call list_issues to pick an open issue (status NEW, ONGOING or REGRESSED), call get_issue and read its investigation block, and when that block names a root cause that was code-verified (found in the repository, not guessed from telemetry alone), call fix_issue with the fingerprint. The answer is the start of the fix, not its result: RUNNING means the fix started and can take half an hour, after which the fix block of get_issue carries the draft pull request link or the reason none was opened. INELIGIBLE carries a reason: for NO_BRIEF call start_investigation, wait until get_issue shows the investigation block, then call fix_issue again; for PR_ALREADY_OPEN read the open pull request's link on get_issue, which is the fix; ISSUE_NOT_OPEN means the issue is resolved or suppressed so there is nothing to fix; ISSUE_UNKNOWN means the fix service could not read the issue's status, so confirm the fingerprint with get_issue. BUSY on another issue means wait for that fix and call again; BUSY on this issue means its own fix is already running, so read its fix block on get_issue. PR_OPENED means the pull request was opened now and its link is on get_issue. FAILED means the fix failed for the reason given; starting again retries only the pull request when a branch was pushed. A fix block ending ALREADY_IN_PROGRESS means the fix found a pull request somebody else opened that already addresses the issue, linked on get_issue: have a person review that one; when it does not fit, call fix_issue again with ignoreExistingPullRequests=true and the fix writes its own. UNAVAILABLE means the fix service did not answer in time and may have started, so read the fix block on get_issue before calling again. NOT_FOUND means the account holds no issue with that fingerprint; NOT_AN_ISSUE means it is a problem on the Overview, which is fixed from its page, not here. DISABLED means the account has not switched fixes on; INVALID_HINT names the hint rule broken. Read next on the answer for what to do. The fix never merges anything: a person reviews the draft pull request.

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": {
      "fingerprint": "<fingerprint>"
    },
    "name": "fix_issue"
  }
}

Input Schema

Name	Required	Description
`hint`	No	One line for the engineer writing the fix, such as where the defect lives or what to leave alone (default none; at most 500 characters, no line break, plain prose only: no [ or ] and no ===)
`fingerprint`	Yes	The issue fingerprint (from list_issues)
`ignoreExistingPullRequests`	No	true to write a fix even though a pull request somebody else opened already addresses the issue (the fix block says ALREADY_IN_PROGRESS); default false, which stops at that pull request and links it

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 26, 2026

addedInput schema / properties / ignoreExistingPullRequests

Added value: +{
+  "description": "true to write a fix even though a pull request somebody else opened already addresses the issue (the fix block says ALREADY_IN_PROGRESS); default false, which stops at that pull request and links it",
+  "type": "boolean"
+}

Changed2 schema fields changedOct 16, 2026
- addedInput schema / $schema
```
Added value: +"https://json-schema.org/draft/2020-12/schema"
```
- removedInput schema / additionalProperties
```
Removed value: -false
```
AddedOct 9, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations declare destructiveHint=true and openWorldHint=true, but the description adds the crucial context the agent cannot get from annotations: this is asynchronous (RUNNING can take half an hour), it never merges anything, a human reviews the draft PR, and a retry after FAILED only re-attempts the pull request when a branch was already pushed. The idempotentHint=true annotation is consistent with the described retry/ALREADY_IN_PROGRESS semantics.

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?

The opening workflow and closing safety note are well front-loaded, but the middle is a dense wall of status-code prose (INELIGIBLE, BUSY, FAILED, ALREADY_IN_PROGRESS, UNAVAILABLE, NOT_FOUND, NOT_AN_ISSUE, DISABLED, INVALID_HINT) that is hard to scan and would be better as a structured status table or output schema. Every sentence is informative, but the single-paragraph packing hurts retrievability.

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?

With no output schema available, the description carries the full burden and does so: it covers prerequisites, async timing, the full status vocabulary with remediation per status, side effects, and the human-review boundary. An agent has everything needed to call this correctly and handle every documented terminal state.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3; the description earns above that by placing fingerprint in the workflow (obtained from list_issues, confirmed via get_issue on ISSUE_UNKNOWN/NOT_FOUND) and by tying ignoreExistingPullRequests=true to the concrete ALREADY_IN_PROGRESS condition. The hint parameter is never mentioned in the description, but the schema documents it fully.

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?

Opens with a precise verb+resource+scope: 'Open a draft pull request that fixes one issue of the caller's account, on the customer's own repository.' This clearly separates it from read-only siblings like get_issue and list_issues, and from start_investigation which it names as a prerequisite in another branch.

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?

Gives an explicit ordered workflow (list_issues → get_issue → verify the investigation block names a code-verified root cause → fix_issue) and states the gating condition ('found in the repository, not guessed from telemetry alone'). It also routes the agent to start_investigation when NO_BRIEF and to the issue's page for NOT_AN_ISSUE, leaving nothing to inference.

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

All Fixter 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.

Resources

Need Help?