Skip to main content
Glama

Preview signafAIde setup for this project (changes nothing)

signafaide_setup

Preview the setup needed to record AI agent tool calls as signed, tamper-evident audit records: detects your stack, then returns the install command and code edit. Writes and sends nothing.

Instructions

Signed, tamper-evident records of what an AI agent decided and did, kept on this machine; nothing is sent until a person opts in. Use when the user asks to audit, log or trace AI or agent decisions, needs an audit trail, tamper-evidence or compliance evidence, or builds an agent whose tools pay, send, approve, delete or change real things. A preview: it changes no file, creates nothing and sends nothing. Returns the detected language, package manager and framework, the exact install command, the code edit for this framework, the functions that look like actions, and what a sandbox would send. Make the edit yourself, run the agent, then call signafaide_verify.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "signafaide_setup"
  }
}

Input Schema

NameRequiredDescriptionDefault
directoryNoPath of the project to work on: the folder the MCP server was started in, or one below it. Default: that folder.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it explicitly guarantees nothing is written, created or sent, and that no data leaves the machine until a person opts in. It enumerates the returned fields, which compensates for the missing output schema. It does not address what happens for an out-of-scope directory or failure behavior.

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?

Sentences are dense and each adds information — scope, triggers, no-side-effect guarantee, return payload, next step. The product framing in sentence one is the only portion not strictly about invoking the tool, so it is not maximally front-loaded but is close.

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 read-only preview with one optional parameter and no output schema, the definition covers what is inspected, what is returned and the follow-up step. It omits failure modes and any boundary behavior for directories outside the server's project root, which keeps it short of fully complete.

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% and the single directory parameter is documented there, including the default and the 'this folder or one below' restriction. The description adds no meaning beyond that, so the baseline of 3 for a well-covered schema is appropriate.

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 description discloses what the preview returns (detected language, package manager, framework, install command, code edit, candidate action functions) and its no-side-effect nature, so the operation is identifiable. However, the opening sentence describes the signafAIde product rather than the tool itself, and the verb ('detect project and produce a setup plan') is only implied by the returns list rather than stated directly.

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?

It gives explicit trigger conditions (user asks to audit, log or trace AI decisions, needs tamper-evidence or compliance evidence, or builds an agent whose tools pay/send/approve/delete), plus a workflow: make the edit, run the agent, then call signafaide_verify. It does not state when to prefer this over siblings such as signafaide_init or signafaide_quickstart, so the routing is incomplete.

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