Skip to main content
Glama
Sign In
falsepass

falsepass

by Super-Eric
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

falsepass_draft

Writes a draft audit report from the last audit run, listing failing probe groups as candidate findings with static hints and marking human-review points. Returns file path and text.

Instructions

Write audits//REPORT.draft.md from the last run: each failing probe group as a candidate finding with the confirmed static hints attached, and the places marked where a person has to judge (defect or design choice, severity). Returns the file path and its text. A draft is not a report: confirm each candidate with falsepass_repro and the reward code first.

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": {
      "env": "<env>"
    },
    "name": "falsepass_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
envYesthe audit's name as falsepass_init returned it: the folder under workdir/audits/
workdirNothe folder whose audits/ holds the audits (default: the current directory).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.15.0

TDQS

A4/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It usefully discloses that this writes a file, returns its path and text, and that findings are unconfirmed candidates requiring human judgment. It omits overwrite/atomicity behavior, permission requirements, and what happens if no prior run exists — meaningful gaps for a write tool.

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?

Three sentences, front-loaded with the action and artifact path, then contents, then return values, then the critical caution. No filler; every sentence carries information the agent needs.

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?

There is no output schema, but the description states what is returned (file path and text), and it explains the draft-versus-report distinction. Missing only edge-case behavior for a tool of this complexity, which is a modest gap rather than a blocking one.

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 100%, so both parameters (env, workdir) are already documented in the schema. The description's '<env>' path template reinforces that env is a folder name under audits/, but adds no syntax or format detail beyond the schema. Baseline 3 applies.

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 (Write) and a concrete, templated resource path (audits/<env>/REPORT.draft.md), plus what the content is (failing probe groups as candidate findings with static hints, human-judgment markers). An agent can distinguish this from falsepass_repro and falsepass_results without opening another schema.

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

Usage Guidelines4/5

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

Explicitly frames this as a drafting step and names the workflow: 'confirm each candidate with falsepass_repro and the reward code first,' which routes the agent to the right sibling. It does not state preconditions (e.g., requiring a prior run) or when not to use it, but the sequencing guidance is clear.

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