Skip to main content
Glama
Sign In

Testsy

by dev.testsy
OverviewDiscussionsAdmin

Draft or revise a plan

plan_test
Read-only

Have the assistant draft a test from a plain-language description, or revise a plan, without saving anything. Returns the proposed steps, checks, values to record, assumptions and any questions only the requester can answer. Show the plan to the requester; to change it, call again with plan and change; to answer questions, pass answers. Once they confirm, pass the plan to create_test. When no question is open the plan has passed the planning review (review.ok). Pass projectId so the assistant knows the project's sign-in accounts and endpoints. Each call uses one assistant draft of the workspace's daily allowance.

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": {
      "description": "<description>"
    },
    "name": "plan_test"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoStart address (https://…); omit for app tests
planNoA plan from an earlier plan_test call, to revise
appIdNoApps: package name or bundle id
changeNoWith plan: what to change, for example "also check the price on the cart page"
answersNoAnswers to the questions of an earlier plan_test call, keyed by question id
platformNoweb (default), android or ios
projectIdNoProject id (p_…), optional
descriptionYesWhat to test, as you would brief a colleague

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Beyond the readOnlyHint and openWorldHint=false annotations, it discloses that nothing is persisted, what the response contains (steps, checks, values to record, assumptions, questions), and a real operational constraint: each call consumes one assistant draft of the workspace's daily allowance. That quota disclosure is exactly the kind of context annotations cannot carry; only minor gaps remain, such as how failures or exhausted allowance are surfaced.

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?

The key constraint (nothing is saved) and the purpose are front-loaded, and every sentence carries a distinct instruction or fact. It is longer than a minimal definition but not padded; the return-value sentence could arguably be tightened, which keeps it off a 5.

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?

With no output schema, the description takes on the burden of describing returns and does so, and it covers the multi-turn conversation model (draft, revise, answer, confirm) plus quota cost. For an eight-parameter, nested-object tool with stateful follow-up calls, an agent has everything needed to invoke it correctly.

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 schema already documents all eight parameters and the baseline is 3. The description nevertheless adds workflow meaning the schema cannot: `plan` + `change` is the revision loop, `answers` is keyed to question ids from a prior call, and projectId exists so the assistant can see the project's sign-in accounts and endpoints.

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?

The description states a specific verb and resource: draft a test from a plain-language description or revise an existing plan, explicitly 'without saving anything'. It distinguishes itself from create_test by naming the handoff point, so an agent can tell the dry-run planner apart from the persisting creation tool without opening either 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?

It gives explicit branches: call again with `plan` and `change` to revise, pass `answers` to respond to open questions, and pass the plan to create_test once the requester confirms. It also states the selection condition for projectId and the meaning of an empty question list (review.ok), leaving little to inference.

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

All Testsy toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources