Skip to main content
Glama

Validate a fix

validate_fix
Destructive

Re-run a finding's attacks against the live target to confirm a fix worked. Returns a verdict: 'resolved' (no attack reproduces anymore), 'still_broken' (at least one still does, or the re-run could not confirm the fix), 'not_eligible' (mark the finding fixed first), or 'validating' (still running). A re-run often takes longer than this call waits, so expect 'validating': then re-read the finding with get_finding until its 'validating' field is false, rather than calling validate_fix again. A second call is refused while one runs, and every call uses one of the finding's 3 re-runs a day. Once 'validating' is false, status 'fixed_verified' means the fix is confirmed, 'regressed' means an attack still reproduces, and 'fixed' means the re-run could not confirm it. Requires the test:run scope.

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": {
      "finding_id": "<finding_id>"
    },
    "name": "validate_fix"
  }
}

Input Schema

NameRequiredDescriptionDefault
finding_idYes

Output Schema

NameRequiredDescriptionDefault
statusYesThe finding's lifecycle status after the validate.
verdictYesresolved: no attack reproduces anymore (finding fixed & verified). still_broken: at least one attack still reproduces, or the re-run could not confirm the fix, in which case the finding stays fixed and awaits the next re-test. not_eligible: mark the finding fixed before validating. validating: still running; re-read the finding with get_finding until its validating field is false.
finding_idYes
replay_run_idYesThe replay run that re-ran the attacks; empty when none was spent.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / properties / verdict / description
      Previous value: -"resolved: no attack reproduces anymore (finding fixed & verified). still_broken: at least one attack still reproduces, or the re-run could not confirm the fix, in which case the finding stays fixed and awaits the next re-test. not_eligible: mark the finding fixed before validating. validating: still running — re-read the finding's status with get_finding."New value: +"resolved: no attack reproduces anymore (finding fixed & verified). still_broken: at least one attack still reproduces, or the re-run could not confirm the fix, in which case the finding stays fixed and awaits the next re-test. not_eligible: mark the finding fixed before validating. validating: still running; re-read the finding with get_finding until its validating field is false."
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true/openWorldHint=true, and the description adds behavior beyond them: the call often returns 'validating' because it outlives the request, a second concurrent call is refused, and each call burns one of three daily re-runs per finding. It also spells out the mapping from verdict strings to finding statuses, which is exactly the kind of consequence detail annotations cannot convey.

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?

Purpose is front-loaded in sentence one, followed by the verdict taxonomy and then the operational caveats. It is dense and slightly run-on, and the verdict labels are restated twice (once as return values, once as resulting statuses), but every clause carries information an agent needs.

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 a one-parameter but asynchronous, quota-limited, destructive mutation, the description covers eligibility, timing, retry/re-read protocol, quota cost, and result interpretation. With an output schema present it need not describe the return payload, and the version/status mapping is provided anyway.

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 coverage is 0% for the single finding_id parameter, so the description must carry meaning. It makes the referent clear (the finding whose attacks are re-run, and which must be marked fixed to be eligible) but never states the identifier's expected form or where to obtain it, leaving a small but real gap.

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 ("Re-run a finding's attacks against the live target to confirm a fix worked") and immediately distinguishes the outcome space from siblings like get_finding by naming it explicitly as the follow-up read path. An agent can tell this apart from passive read tools without opening the schema.

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?

Explicitly covers when to use (confirm a fix), when not to ("mark the finding fixed first" for the not_eligible case), and names the alternative action after the call ("re-read the finding with get_finding ... rather than calling validate_fix again"). It also states the prerequisite scope (test:run) and the refusal condition for concurrent calls.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources