Skip to main content
Glama

still_point

Pause and reflect on a file or code snippet to let the answer come naturally.

Instructions

[Buddy Tool] Stop. Be still. Let the answer come to you. (global)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
targetNoThe file or code to look at

Implementation Reference

  • The 'makeTool' generic factory that creates the handler for 'still_point' (and other stat tools). The handler sets petBuddyStreak=0, updates lastToolCalled, then delegates to 'respond()' with the PATIENCE stat and 'still' context.
    function makeTool(
      toolName: string,
      description: string,
      stat: keyof typeof STAT_TOOL_RESPONSES,
      context: string,
    ): void {
      dynamicTools.set(toolName, {
        tool: { name: toolName, description, inputSchema },
        handler: async (args) => {
          S.petBuddyStreak = 0;
          S.lastToolCalled = toolName;
          return respond(stat, context, args);
        },
  • The 'respond' function that executes the actual tool logic for 'still_point'. It picks a random quip from STAT_TOOL_RESPONSES['PATIENCE']['still'] (the 'still' context responses like 'Stop moving. Let the problem come to you.'), optionally appends a target, and wraps the result in buddy display tags.
    function respond(
      stat: keyof typeof STAT_TOOL_RESPONSES,
      context: string,
      args: Record<string, unknown>,
    ): string {
      const buddy = S.currentBuddy;
      if (!buddy) return 'No buddy active. Initialize a buddy first.';
      const pool = STAT_TOOL_RESPONSES[stat][context] ?? STAT_TOOL_RESPONSES[stat]['general']!;
      const quip = pick(pool);
      const target = args['target'] as string | undefined;
      const output = target
        ? `${buddy.name}: "${quip}"\n\n*target: ${target}*`
        : `${buddy.name}: "${quip}"`;
      return wrapBuddyDisplay(output);
    }
  • Registration of 'still_point' tool: calls makeTool with name='still_point', description for the PATIENCE stat, context='still'.
    makeTool(
      'still_point',
      '[Buddy Tool] Stop. Be still. Let the answer come to you. (global)',
      'PATIENCE',
      'still',
    );
  • Input schema for 'still_point' (and all stat tools) — accepts an optional 'target' string parameter.
    const inputSchema = {
      type: 'object' as const,
      properties: { target: { type: 'string', description: 'The file or code to look at' } },
    };
  • The 'still' response pool for the PATIENCE stat — these are the quips randomly selected when 'still_point' is called. They are part of STAT_TOOL_RESPONSES['PATIENCE']['still'].
      still: [
        'Stop moving. Let the problem come to you.',
        "Do nothing for 30 seconds. I'll time it.",
        'The answer arrives when you stop looking.',
        "Stillness. Not giving up. There's a difference.",
      ],
    },
Behavior1/5

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

No annotations provided; description does not disclose any behavioral traits (e.g., what happens when invoked, if it modifies state, if it requires authentication).

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?

Description is short but lacks necessary detail. It is concise but not sufficiently informative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple schema and lack of annotations, the description should explain the tool's effect and return behavior. It fails to do so, leaving major gaps.

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 coverage is 100% with a clear description for the sole parameter. The tool description adds no additional meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description is vague and poetic ('Stop. Be still. Let the answer come to you. (global)'). It does not clearly state what the tool does, though the schema suggests it involves looking at a file or code.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool vs siblings like buddy_talk or zen_mirror. The '(global)' hint is insufficient.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Lyellr88/buddy-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server