Skip to main content
Glama

body_skill_save

Save a learned procedure as a reusable skill with steps, rationale, and verification status. Unverified skills stay proposals, so learned work is replayed only after results are checked.

Instructions

Save a procedure you learned from your own work, so it can be replayed.

steps: the same action schema hands_batch uses (click/type/fill/goto/verify...). why: what you learned and why it works - this is the part that makes it a skill and not a script. verified: only true if the result was actually checked. An unverified skill stays a proposal and is never replayed blindly.

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": {
      "name": "<name>",
      "goal": "<goal>",
      "steps": "<steps>"
    },
    "name": "body_skill_save"
  }
}

Input Schema

NameRequiredDescriptionDefault
whyNo
goalYes
nameYes
tagsNo
stepsYes
verifiedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description carries the full behavioral burden. It does disclose one meaningful trait — an unverified skill stays a proposal and is never replayed blindly — which is real behavior beyond the schema. However, it says nothing about overwrite semantics for an existing name, persistence, permissions, or what is returned on save.

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 purpose is front-loaded in one sentence, followed by tight parameter notes in a consistent 'field: meaning' pattern. The hands_batch cross-reference is an efficient way to specify step shape. Slightly list-like rather than prose, but zero wasted words.

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

Completeness3/5

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

For a mutation tool with no annotations and no output schema, the definition covers the conceptual core (why a skill differs from a script, what verified gates) but not the operational edges. Three of six parameters are undocumented and the result of a save call is unexplained, leaving real 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 0% across 6 parameters, so the description must compensate and only partly does. It meaningfully explains 'steps' (same action schema as hands_batch, with examples), 'why' (the differentiator from a script), and 'verified' (only true if the result was checked), but leaves name, goal, and tags entirely undocumented.

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?

States a specific verb and resource: 'Save a procedure you learned from your own work, so it can be replayed'. The replayability clause distinguishes it from the sibling read/replay tools without naming them explicitly. An agent knows what it writes, though it isn't told the sibling it is not (body_skill_list / body_skill_replay).

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?

Usage is implied by 'a procedure you learned from your own work' — capture something worth repeating — but there is no explicit when-to-use vs when-not, nor any statement about how this differs from body_workflow_note or body_lessons. The agent must infer the trigger condition.

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