thinkhard.si prompt tools

Grade a prompt out of 10

grade_prompt

Read-onlyIdempotent

Score a prompt out of 10 on the ten checks thinkhard.si uses (what to make, who it is for, background facts, length, format, what to avoid, what good looks like, an example, what to do if unsure, layout for the model). Returns which checks pass and a plain question for each one that fails. It also reads the prompt against the expert prompts in the repository: which task it is, which of that task's inputs are there (a resume, a job posting, a policy), how ready it is for that task out of 10, and the three changes that would help most. Use it to see what a prompt is missing before improving it. The prompt is read to answer and is not stored.

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": {
      "prompt": "<prompt>"
    },
    "name": "grade_prompt"
  }
}

Input Schema

Name	Required	Description	Default
`prompt`	Yes	The prompt to grade (the user message).
`system`	No	Optional system prompt, graded together with the prompt.
`target`	No	The model it is for. Layout is judged for this model.	any

Output Schema

Name	Required	Description
`band`	Yes	The score in a word.
`score`	Yes	Out of 10.
`checks`	Yes	The ten checks, in order.
`engine`	No
`target`	Yes	The model it was read for.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 3, 2026

addedOutput schema / properties / engine / properties / fill

Added value: +{
+  "additionalProperties": {
+    "type": "string"
+  },
+  "description": "The user's own material from the prompt, matched to the expert prompt's blanks by name. Pass it to get_prompt as values to start from the expert prompt with these already filled in.",
+  "type": "object"
+}

Changed1 schema field changedOct 31, 2026

addedOutput schema / properties / engine

Added value: +{
+  "properties": {
+    "inputs": {
+      "description": "What this task needs, in the expert prompt's order.",
+      "items": {
+        "properties": {
+          "label": {
+            "type": "string"
+          },
+          "name": {
+            "description": "The input's blank name in the expert prompt.",
+            "type": "string"
+          },
+          "status": {
+            "description": "given; missing; mentioned (named but not pasted in); blank (left as {{name}}); optional (missing, and the task works without it).",
+            "enum": [
+              "given",
+              "missing",
+              "mentioned",
+              "blank",
+              "optional"
+            ],
+            "type": "string"
+          }
+        },
+        "required": [
+          "name",
+          "label",
+          "status"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "match": {
+      "description": "How the task was found: template (the prompt started from that thinkhard.si template), sure, likely or unsure; none when the repository has no such task, and readiness then rests on the ten checks alone.",
+      "enum": [
+        "template",
+        "sure",
+        "likely",
+        "unsure",
+        "none"
+      ],
+      "type": "string"
+    },
+    "next": {
+      "description": "The changes expected to raise readiness most, best first, at most three.",
+      "items": {
+        "properties": {
+          "ask": {
+            "description": "What to add, in plain words.",
+            "type": "string"
+          },
+          "expert": {
+            "description": "How the expert prompt for this task handles it.",
+            "type": "string"
+          },
+          "kind": {
+            "enum": [
+              "input",
+              "check"
+            ],
+            "type": "string"
+          },
+          "label": {
+            "type": "string"
+          },
+          "name": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "kind",
+          "name",
+          "label",
+          "ask"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "others": {
+      "description": "Other tasks it might be when the match is not sure, or the nearest ones when no task fits.",
+      "items": {
+        "properties": {
+          "slug": {
+            "type": "string"
+          },
+          "title": {
+            "type": "string"
+          },
+          "url": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "slug",
+          "title",
+          "url"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "readiness": {
+      "description": "Out of 10: how ready the prompt is for this task, from the ten checks weighed for it and the inputs it needs.",
+      "type": "integer"
+    },
+    "task": {
+      "properties": {
+        "collection": {
+          "type": "string"
+        },
+        "slug": {
+          "description": "Pass it to get_prompt for the expert version.",
+          "type": "string"
+        },
+        "title": {
+          "type": "string"
+        },
+        "url": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "slug",
+        "title",
+        "collection",
+        "url"
+      ],
+      "type": "object"
+    }
+  },
+  "required": [
+    "readiness",
+    "match",
+    "next"
+  ],
+  "type": "object"
+}

Changed1 schema field changedOct 23, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "band": {
+      "description": "The score in a word.",
+      "type": "string"
+    },
+    "checks": {
+      "description": "The ten checks, in order.",
+      "items": {
+        "properties": {
+          "check": {
+            "type": "string"
+          },
+          "pass": {
+            "type": "boolean"
+          }
+        },
+        "required": [
+          "check",
+          "pass"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "score": {
+      "description": "Out of 10.",
+      "type": "integer"
+    },
+    "target": {
+      "description": "The model it was read for.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "score",
+    "band",
+    "target",
+    "checks"
+  ],
+  "type": "object"
+}

First observedOct 23, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely new context: 'The prompt is read to answer and is not stored,' which tells the agent about data retention, and it discloses that failures are returned as plain questions rather than opaque scores. It does not discuss limits on prompt size or error behavior.

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 purpose is front-loaded, which is good, but the description runs as one long paragraph with a ten-item parenthetical list that is dense and hard to scan. The returns, repository comparison, and usage sentences each earn their place individually, yet the overall block could be tightened into shorter, separated statements.

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 annotations covering safety and an output schema covering return shape, the description is nearly complete: it explains scoring basis, failure reporting, cross-referencing against expert prompts, and data handling. Minor gaps remain around prompt length limits and behavior when no repository task matches.

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 prompt, system, and the target enum. The description reinforces that layout is judged against the target model but adds no format or syntax detail beyond the schema, and never mentions the optional system parameter; baseline 3 applies.

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 and resource ('Score a prompt out of 10') and then enumerates the exact criteria used, plus a second capability: reading the prompt against expert prompts in the repository to identify task, present inputs, readiness, and top three improvements. This is clearly distinguishable from siblings like get_prompt or search_prompts, which retrieve rather than evaluate.

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?

'Use it to see what a prompt is missing before improving it' gives a clear situation and implicitly positions grading ahead of the fix_bad_answer sibling. It does not name alternatives explicitly or state when not to use it (e.g., for prompts outside the repository's task coverage), which keeps it below a 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?