Skip to main content
Glama
Sign In
AnyBridge

AnyBridge

by ps-aditya
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

propose_workflow

Read-only

Submit a workflow plan with steps and checks for validation before execution. Returns a plan ID, hash, risk summary, or fixable errors without running any actions.

Instructions

Submit a plan. Does NOT run it. Each step: {id, action: , args, expect}. Each check says how to prove success. Returns plan_id, hash, risk summary, or fixable errors.

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": {
      "intent": "<intent>",
      "steps": "<steps>",
      "checks": "<checks>"
    },
    "name": "propose_workflow"
  }
}

Input Schema

NameRequiredDescriptionDefault
stepsYes
checksYes
intentYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description is consistent with them by stating the plan is not executed. It adds real behavioral value beyond the annotations by disclosing the return payload (plan_id, hash, risk summary) and the failure mode (fixable errors), which tells the agent this call is safe to retry after correction.

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?

Front-loaded and near waste-free: the first two sentences carry the most important distinction, then the structural hints. The telegraphic style ('Each check says how to prove success') is slightly ambiguous, but nothing is redundant.

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

Completeness3/5

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

For a 3-required-parameter tool with deep nested objects, 0% schema coverage and no output schema, the description covers the return shape well but leaves the required 'intent' field and the 'effect'/'kind' fields unexplained. An agent would still be guessing about valid check kinds and how intent is used in risk analysis.

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 0%, so the description must carry parameter meaning, and it partially does: it explains the step shape ({id, action: <menu id>, args, expect}) and signals that 'action' references a menu id. It leaves 'intent' undefined, omits the 'effect' field present in the schema, and describes checks only vaguely ('says how to prove success') without explaining 'kind' or 'params'.

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+resource ('Submit a plan') and immediately rules out the most likely confusion with 'Does NOT run it', which cleanly separates it from the execute_workflow sibling. An agent can tell what this tool produces (a validated plan) 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 Guidelines3/5

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

The negative framing 'Does NOT run it' implies this is a dry-run/validation step that precedes execution, which is useful implied routing. However, it never names execute_workflow or states the ordering explicitly, nor does it say what to do with the returned plan_id or when to skip this step.

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