Skip to main content
Glama
Sign In

thinkhard.si prompt tools

by si.thinkhard
OverviewDiscussionsAdmin

Search the prompt repository

search_prompts
Read-onlyIdempotent

Search the thinkhard.si repository of 1,024 tested prompt templates for work tasks: email, meetings, presentations, job search, marketing, sales, support, HR, finance, legal, spreadsheets, research and more. Use it when the user wants a prompt for something to write, plan, summarize, analyze or draft at work. Returns the best matches first, each with the slug that get_prompt takes.

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": {
      "query": "<query>"
    },
    "name": "search_prompts"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoOptional: how many prompts to return, best match first (1 to 25, default 8).
modelNoOptional: only prompts laid out for this kind of model.
queryYesWhat the user wants to do, in plain words, for example "cover letter" or "summarize a long contract". Everyday words, abbreviations (CV, 1:1, P&L, SOP) and typos are understood, and results come best match first.
collectionNoOptional: limit to one collection (see list_collections).

Output Schema

NameRequiredDescriptionDefault
promptsYesBest match first. Empty when nothing matches.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / limit / description
      Added value: +"Optional: how many prompts to return, best match first (1 to 25, default 8)."
  2. Changed1 schema field changed
    • changedInput schema / properties / query / description
      Previous value: -"What the user wants to do, in plain words, for example \"cover letter\" or \"summarize a long contract\"."New value: +"What the user wants to do, in plain words, for example \"cover letter\" or \"summarize a long contract\". Everyday words, abbreviations (CV, 1:1, P&L, SOP) and typos are understood, and results come best match first."
  3. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "prompts": {
+      "description": "Best match first. Empty when nothing matches.",
+      "items": {
+        "properties": {
+          "collection": {
+            "description": "The collection it belongs to.",
+            "type": "string"
+          },
+          "id": {
+            "description": "Registry number, such as CAR-002.",
+            "type": "string"
+          },
+          "laid_out_for": {
+            "description": "The kind of model it is laid out for.",
+            "type": "string"
+          },
+          "score": {
+            "description": "Its own grade out of 10.",
+            "type": "integer"
+          },
+          "slug": {
+            "description": "Pass it to get_prompt.",
+            "type": "string"
+          },
+          "title": {
+            "type": "string"
+          },
+          "url": {
+            "description": "Its page on thinkhard.si.",
+            "type": "string"
+          },
+          "use": {
+            "description": "When to use it.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "id",
+          "slug",
+          "title",
+          "use",
+          "collection",
+          "laid_out_for",
+          "score",
+          "url"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "prompts"
+  ],
+  "type": "object"
+}
  4. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds useful behavior beyond that: results are returned best-match first and each carries a slug usable by get_prompt, which tells the agent how to chain calls. It does not discuss result limits or empty-result behavior, keeping it below 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.

Conciseness4/5

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

Two sentences, front-loaded with the resource and scope, then the usage trigger and the return handoff. The long enumeration of domains is slightly listy but earns its place by aiding retrieval matching. No filler or restated title.

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 an output schema present, the description needn't explain return values, and the four parameters are fully documented in the schema. The description covers purpose, trigger, result ordering and the get_prompt handoff, leaving nothing an agent needs in order to call it correctly.

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%, including the fuzzy-matching note for query, the limit range, the model enum and the collection enum, so the schema already carries parameter meaning. The description adds no additional syntax or constraint information beyond what the schema states. 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 (search a named repository of 1,024 tested prompt templates) and scopes it with concrete work-task domains, so an agent knows exactly what corpus is being queried. The closing line ties it to the sibling get_prompt by explaining that results carry the slug that tool consumes, giving a clear boundary between searching and fetching.

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?

Explicitly says when to use it: "when the user wants a prompt for something to write, plan, summarize, analyze or draft at work." It also implies the follow-up step via get_prompt. It stops short of naming when NOT to use it or pointing at alternatives such as list_collections for browsing, so it is clear but not fully exclusionary.

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 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