headlo-mcp

Official

Overview Schema Source Related Servers Discussions Admin

cap_capture_expert

Run an existing CAP as a live guided interview. Provide the CAP ID, respond to each question, and get a synthesized answer built from the accumulated knowledge pairs.

Instructions

Run an existing CAP (Context Accumulation Protocol) as a live intake session. Pass cap_id and an empty message to load and start the first question. Answer each question in subsequent calls. On completion returns a synthesized answer built from the CAP knowledge pairs. Returns { response, session_state, complete, answer? } as JSON.

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": {
      "cap_id": "<cap_id>"
    },
    "name": "cap_capture_expert"
  }
}

Input Schema

Name	Required	Description
`cap_id`	Yes	12-char CAP ID to run
`message`	No	Empty string on first call. Your answer to the current question on subsequent calls.
`session_state`	No	Opaque state from the previous response — pass back unchanged

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.2Aug 6, 2026

TDQS

A4.4/5.0

Behavior4/5

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

With no annotations, the description carries the full burden. It discloses that this is a stateful session requiring session_state to be passed back, and it describes the final return shape. It does not mention error handling or side effects, but for a non-destructive capture tool, the transparency is solid.

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

Conciseness5/5

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

The description is four sentences, front-loaded with the primary purpose, and includes the return shape without redundancy. Every sentence adds value, and there is no filler.

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?

Given the tool's interactive nature and lack of output schema, the description explains how to start, continue, and finish the session, and lists the return fields. It lacks explicit error scenarios or preconditions, but it covers the core workflow sufficiently for an agent to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the description adds macro-level semantics by tying the parameters into a workflow: empty message starts, message answers, session_state loops. This goes beyond the per-parameter descriptions in the schema, which are already detailed; the description reinforces the session protocol.

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 clearly states the tool's purpose: 'Run an existing CAP (Context Accumulation Protocol) as a live intake session.' It specifies the exact verb and resource, and the interactive flow distinguishes it from sibling tools like create_expert_protocol and cap_edit_expert.

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?

The description provides concrete usage guidance: pass cap_id and an empty message to start, answer each question in subsequent calls, and pass back session_state. It does not explicitly name alternatives but the usage pattern is unambiguous and context-rich.

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