thinkhard.si prompt tools

Audit a whole prompt library

audit_library

Read-onlyIdempotent

Read many prompts at once, such as a team's shared prompt doc: each prompt's score on the ten checks, the task it does and how ready it is for it, near-copies with the one to keep, private details that should not be in a shared prompt (emails, phone numbers, card numbers, keys), which collections the library covers and the expert prompts it lacks, a health score, and which prompts to fix first.

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": "audit_library"
  }
}

Input Schema

Name	Required	Description	Default
`text`	No	Or many prompts in one text, separated by lines of three dashes.
`prompts`	No	The prompts, up to 300.

Output Schema

Name	Required	Description
`gaps`	Yes	Expert prompts in the library's own collections that it does not have.
`prompts`	Yes	Every prompt: score, readiness, task, what it misses, private details, which it copies.
`summary`	Yes
`clusters`	Yes	Near-copies, with the one to keep.
`coverage`	Yes
`fix_first`	Yes	What to fix first, weakest on the tasks used most.
`distribution`	Yes	How many prompts score 1, 2 … 10.

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 4, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already declare read-only, non-destructive, idempotent, closed-world behavior. The description adds substantial analytical context—scoring against ten checks, detecting near-copies, finding private details, assessing collection coverage, and prioritizing fixes—though it does not clarify how the two optional input modes are handled when both or neither are supplied.

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 description is front-loaded with the core action and then lists audit outputs efficiently in a single sentence. It is dense but every clause identifies a distinct part of the audit result, with little wasted wording.

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 batch audit with a full input schema and an output schema, the description covers the analytical scope thoroughly enough to set expectations. The main missing piece is sibling routing—when to use this versus lint_prompts or grade_prompt—rather than return-value detail.

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 the schema already documents the two inputs and the 300-prompt limit. The description confirms batch input but does not add meaning beyond the schema, such as the relationship between the 'text' and 'prompts' parameters or which is preferred.

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 clearly states the tool reads and audits many prompts at once, listing the specific analyses it returns. It implies a batch/library scope that separates it from single-prompt siblings like grade_prompt, but it does not explicitly name or contrast those alternatives.

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 phrase 'such as a team's shared prompt doc' gives an implied batch-audit use case, but there is no explicit guidance on when to choose this over lint_prompts, grade_prompt, or search_prompts, nor any stated exclusions.

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?