Skip to main content
Glama

Read a skill

skills__get
Read-onlyIdempotent

One skill's instructions (its SKILL.md) and the list of files it carries. Follow the instructions for the job; read a file it points to with file. Long text comes in parts: when next_offset is not null, call again with offset set to it. A skill never widens what you may do: changes to sites still wait for a person's approval. Reads Royally's records only.

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>"
    },
    "name": "skills__get"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNoA file path from the skill’s files, such as references/guide.md, to read that file instead of SKILL.md.
nameYesThe skill name from skills/list.
offsetNoWhere to continue a long text, from next_offset.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already declare this a safe, idempotent read, and the description still adds substantive behavior beyond them: the pagination contract (when `next_offset` is non-null, call again with `offset`), the guarantee that a skill never expands the agent's permissions and that site changes still need human approval, and the data boundary ("Reads Royally's records only"). Those are things an agent could not infer from annotations or schema.

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?

Three tight sentences, front-loaded with what is returned, then how to page, then the permission caveat. No filler; each sentence carries distinct information.

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?

Covers return contents, pagination, permission scope, and data boundary for a three-parameter read with no output schema, which is nearly everything an agent needs. Minor ambiguity remains about whether the file list is still returned when `file` is supplied.

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%, so the baseline is 3, but the description adds real meaning on top: it explains that `file` selects an alternate document instead of SKILL.md and ties `offset` to the returned `next_offset` as a continuation token. Only the `name` parameter's origin (skills__list) is left to the schema.

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: it returns one skill's SKILL.md instructions plus the list of files that skill carries. The word "One" implicitly distinguishes it from the skills__list sibling, though no sibling is named explicitly.

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?

Gives concrete operating guidance: follow the returned instructions for the job, and use the `file` parameter to read a referenced file rather than the SKILL.md. It also tells the agent exactly when to re-call for pagination. It does not explicitly say when to prefer skills__list over this tool, so it stops short of full routing guidance.

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