Skip to main content
Glama

List Skills

list_skills
Read-onlyIdempotent

List the caller's resolved active skill set — exactly one entry per name (a project-scoped activation for the given project_key shadows an account-wide one, own content shadows a first-party Library skill of the same name). Names, descriptions, origin, and version only — not full bodies. Pass mode: "catalog" to browse the public Gryz Skill Library instead of the caller's activations. Read-only.

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": "list_skills"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNo"catalog" browses the public Gryz Skill Library instead of your own activations. Default: your active set.
project_keyNoCurrent repo project_key — a project-scoped activation for this key shadows an account-wide one of the same name

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the trailing 'Read-only' is redundant. What the description adds beyond annotations is real: the shadowing/precedence semantics that determine which entry survives, and the explicit payload boundary ('Names, descriptions, origin, and version only — not full bodies'). It does not discuss ordering or volume limits, which keeps it from a 5.

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 critical scoping and resolution rule is front-loaded in the first sentence, with mode routing and payload limits following. It is dense but every clause carries information; the only waste is the closing 'Read-only,' which duplicates annotations.

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 no output schema, the description compensates by naming the returned fields and explicitly excluding skill bodies, and it explains the resolution behavior that makes the list non-obvious. Minor gaps remain: nothing about ordering, pagination, or what catalog mode returns structurally.

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 100%, so both mode and project_key are already documented in the schema, and the description largely restates them (including the same shadowing note for project_key). Baseline 3 is appropriate; the description adds emphasis but no new syntax, format, or validation detail.

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 names a specific verb and resource ('List the caller's resolved active skill set') and immediately pins down the resolution rule (one entry per name, project-scoped shadows account-wide, own content shadows Library skill). It also distinguishes the two operating modes, so an agent can tell this apart from create_skill/fork_skill/delete_skill without opening the schema.

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?

It gives clear conditional guidance for the alternative mode: pass mode="catalog" to browse the public Gryz Skill Library instead of activations, with the default being the caller's active set. It does not state exclusions relative to sibling tools (e.g., when to prefer a skill-detail fetch over this list), but the mode routing is explicit.

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.