thinkhard.si prompt tools

Plan a bigger job as a chain of prompts

plan_workflow

Read-onlyIdempotent

Turn a job such as hiring for a role, launching a feature, closing the month or applying for a job into steps in the order the work happens, each with the expert prompt from the repository that does it, which earlier answer it takes and into which blank, and the details to gather once for all of them. Works from a one-line description (matched to a playbook of how that kind of work goes) or from steps listed one per line. Use it when a request is too big for one prompt, then work through the steps with get_prompt.

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": {
      "job": "<job>"
    },
    "name": "plan_workflow"
  }
}

Input Schema

Name	Required	Description
`job`	Yes	The job in plain words, or its steps one per line.
`material`	No	Optional material the steps can use, such as a job posting or notes.
`max_steps`	No	Optional: the most steps to return.

Output Schema

Name	Required	Description
`steps`	Yes	The steps in order.
`waves`	Yes
`gather`	Yes	Details to give once, with the steps that use each.
`values`	Yes	Blanks already filled from the description or material, by name.
`summary`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 4, 2026

TDQS

A4/5.0

Behavior4/5

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

The annotations already establish this as read-only, idempotent, non-destructive and closed-world, so the description only needs to add operational context, which it does: it lists both accepted input modes (a one-line description matched against a playbook, or steps one per line) and describes the shape of each returned step, including dependency and shared-detail fields. It does not address playbook coverage limits or what happens when a description matches no playbook, which is why it is a 4 rather than a 5.

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

Conciseness3/5

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

The opening sentence is a roughly sixty-word run-on that packs the output shape, dependency mapping and shared-detail concept into one clause chain, making it harder to parse than it needs to be. There is no filler and the usage guidance is correctly placed at the end, but the structure would benefit from splitting the behavioral claims into separate sentences.

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?

With an output schema present, return values need not be explained, and the annotations already cover the safety profile, so the description's remaining job is input modes and step structure, both of which are covered. The only gap is edge-case behavior, such as an unmatched one-line description or a step list that exceeds max_steps.

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%, so all three parameters are already documented and the baseline is 3. The description adds marginal value by reframing the job parameter as either a prose description or a line-per-step list, and by characterizing material as 'details to gather once for all of them', but it does not explain how max_steps affects playbook-derived plans or how material interacts with per-step prompts.

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 names a specific verb and resource: turn a job (hiring, launching a feature, closing the month) into ordered steps, each bound to an expert prompt, its dependency on an earlier answer, and its input blank. That is far more determinate than the sibling names (search_prompts, get_prompt, grade_prompt) and an agent can tell it apart from them without opening any 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?

It states the triggering condition clearly ('Use it when a request is too big for one prompt') and names the follow-on tool for execution ('then work through the steps with get_prompt'), which is exactly the routing an agent needs. It stops short of explicit exclusions, e.g. what to do instead for a single-prompt task, so it falls just below a full 5.

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

All thinkhard.si prompt tools tools Inspect

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

Need Help?