Skip to main content
Glama

asset_scan_resolve

Resolve a secret-scan finding that blocked a file by recording the user’s explicit allow (false positive) or exclude decision, with their quote for audit.

Instructions

Answer a secret-scan hit that held a file back. Only on the user's explicit word.

Never decide this yourself: show the user the file, rule and line from asset_backup_status and ask. "allow" (the user says it is a false positive) uploads that exact content; a later edit is scanned again. "exclude" stops backing up that file for good. The answer is audited with the user's words.

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>",
      "action": "<action>",
      "user_quote": "<user_quote>"
    },
    "name": "asset_scan_resolve"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYes"allow" or "exclude", as the user decided
finding_idYesThe finding_id from asset_backup_status
user_quoteYesThe user's own words deciding it, verbatim (recorded in the audit event)

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.17.1

TDQS

A4.1/5.0
Behavior3/5

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

With no annotations present, the definition carries the full burden, and it does substantially better than most: it discloses the permanent effect of "exclude" ("stops backing up that file for good"), the partial effect of "allow" ("uploads that exact content; a later edit is scanned again"), and the audit consequence tied to user_quote. What it omits is scope and side effects: no permission or role requirement, no indication of what the call returns or how errors (e.g. an unknown or already-resolved finding_id) behave, and no statement of whether the decision can be reversed after the fact. Those gaps keep a mutation tool with zero annotation coverage at mid range rather than higher.

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

Conciseness5/5

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

The critical constraint (only on the user's explicit word, never decide alone) is front-loaded in the first two lines. Every subsequent sentence carries a distinct behavioral fact: what allow does, what exclude does permanently, and what gets audited. There is no restatement of the schema and no filler.

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

Completeness4/5

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

For a three-required-parameter mutation tool with an output schema and no annotations, the definition covers the decisive things an agent needs: the human-in-the-loop prerequisite, the difference between the two actions, permanence of exclude, and the audit trail. Return values need not be explained because an output schema exists. It falls short of complete only on permissions/authorization context and on what happens when the supplied finding_id is stale or invalid.

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, but the description earns more by ascribing meaning to both action values ("allow" = user says it is a false positive; "exclude" = stop backing up for good) and by explaining that the later re-scan only happens for allowed content. The user_quote constraint -- the user's own words, verbatim, recorded in the audit -- reinforces what the schema already says about the audit event. Only finding_id gets no extra treatment beyond pointing back to asset_backup_status, which is already in the schema description.

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

Purpose4/5

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

The definition opens with a concrete verb-plus-resource statement ("Answer a secret-scan hit that held a file back") and makes clear that the tool resolves a blocked file rather than reporting status, so an agent can separate it from asset_backup_status. The wording is somewhat metaphorical ("answer a hit"), but the two allowed outcomes are named immediately in the next lines, so there is no ambiguity about what the operation does.

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?

It provides an explicit precondition ("Only on the user's explicit word"), a prohibition ("Never decide this yourself"), and the exact procedure for getting there: show the file, rule and line from asset_backup_status and ask the user. It also clarifies the circumstances that select each action: "allow" is for a false positive, "exclude" is for the user who wants the file no longer backed up. This is a model of when/when-not guidance with the alternative path named.

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

Deploy Server

Other Tools