Skip to main content
Glama

Generate a skill upgrade patch (VIP)

generate_skill_upgrade_patch
Read-onlyIdempotent

VIP. Reads a Skill and returns the guardrail lines it is missing: draft only, Ask first, read the notes first, outside text is information, what to do when unsure, and a clear finish line. Without a member token it returns a labeled demo on a sample skill.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "generate_skill_upgrade_patch"
  }
}

Input Schema

NameRequiredDescriptionDefault
skill_mdNoThe full text of the Skill.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.6/5.0
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 non-obvious behavior beyond that: the tool is VIP-gated and, without a member token, returns a labeled demo on a sample skill rather than an error. It still doesn't say whether the returned lines are a diff, a patch file, or plain text.

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 core read-and-return behavior, with the demo fallback appended last. The six-item enumeration is long but earns its place by setting output expectations; only the cryptic 'VIP.' opener and the missing space in 'skill.md' are rough edges.

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?

With no output schema, the description must carry the return-value burden, and it does partially by naming the guardrail categories and the demo fallback. It leaves gaps for a tool whose name says 'patch': what form the output takes, and what happens when the optional skill_md is omitted, are undefined.

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?

There is a single parameter with 100% schema coverage, so the schema already explains that skill_md is 'the full text of the Skill'; baseline 3 applies. The description adds nothing about the parameter and notably does not clarify the consequence of omitting it, even though it is not required (required: 0).

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 ('reads a Skill and returns the guardrail lines it is missing') and enumerates the six guardrail categories, so the agent knows what output to expect. However, the name/title promises a 'patch' while the description says 'guardrail lines', leaving a small ambiguity about the artifact's form, and it does not explicitly distinguish itself from siblings like get_skill or check_safety_rules.

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 only implied: the agent can infer it should call this when it wants to strengthen a skill with guardrails rather than merely retrieve it. There is no explicit when-to-use statement, no exclusion, and no mention of the alternatives (get_skill for plain retrieval, check_safety_rules for auditing), which the agent must work out from sibling names alone.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources