Skip to main content
Glama
MCP Agent Operations

MCP Agent Operations

skill_load

Read-onlyIdempotent

Loads ordered skills by name and optionally appends resolved extensions, letting agent operations assemble required capabilities in one call.

Instructions

Load skills and optionally append independently resolved extensions.

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": {
      "names": "<names>"
    },
    "name": "skill_load"
  }
}

Input Schema

NameRequiredDescriptionDefault
namesYesOne to thirty-two unique base skill names in required order.
include_extensionsNoSearch for each `<name>.extension` through normal catalog precedence and append available extensions. Defaults to false.

Output Schema

NameRequiredDescriptionDefault
okYes
errorsNo
skillsNo
catalog_revisionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.11.0
    • addedInput schema / properties / include_extensions
      Added value: +{
      +  "default": false,
      +  "description": "Search for each `<name>.extension` through normal catalog\nprecedence and append available extensions. Defaults to false.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / names / description
      Added value: +"One to thirty-two unique base skill names in required order."
    • changedOutput schema / properties / skills / items / description
      Previous value: -"Return one model-facing skill document without exposing host filesystem paths."New value: +"Return one model-facing skill document without exposing host filesystem paths.\n\n`digest` identifies the exact returned `content`. When extension lookup is enabled,\n`applied_extensions` names each precedence-resolved extension appended to that content.\nSupporting resources remain owned and addressable by their individual catalog skill."
    • addedOutput schema / properties / skills / items / properties / applied_extensions
      Added value: +{
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
  2. First observedv0.5.1

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so safety is covered. The description adds one useful behavioral nugget — that extensions are resolved independently through catalog precedence and appended — but says nothing about failure modes (missing/invalid names), ordering guarantees, or whether loading is cached.

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?

A single front-loaded sentence with no filler: verb, resource, and the key optional behavior. Nothing is redundant or buried.

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?

With an output schema covering return values, full parameter documentation, and rich annotations, the main remaining gap is sibling disambiguation and error behavior for unknown skill names. Those are real but modest for what is essentially a simple batch read operation.

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%, so both parameters are already documented, including the 1–32 unique-name constraint and the default of false for include_extensions. The description only reinforces the optional-extension semantics ('independently resolved extensions'), which adds little beyond the schema's 'normal catalog precedence' wording.

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?

The description gives a specific verb and resource ('Load skills') plus the optional extension-append behavior, which is more than a tautology. It does not explicitly distinguish itself from siblings like skill_read, skill_list, or skill_resource_load, leaving the agent to infer that this is a batch loader keyed by names.

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?

There is no statement of when to use this tool, when not to, or which sibling to prefer (skill_read, skill_list, skill_resource_load, reference_load). The only usage signal is the word 'Load' and the optional extension flag, which is implied rather than explained.

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