Skip to main content
Glama

Update Skill

update_skill
DestructiveIdempotent

Write a new version of a skill you own (never mutates a prior version). Fails on a skill you do not own — call fork_skill first to get an editable copy. Supports rollback_to_version to restore an earlier version as a new, audited version.

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": {
      "id": "<id>"
    },
    "name": "update_skill"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYes
bodyNo
titleNo
descriptionNo
rollback_to_versionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the safety profile is largely covered. The description still adds real value by explaining that prior versions are preserved and that failure occurs on non-owned skills, but it never reconciles the 'destructive' annotation with its own 'never mutates' claim, and says nothing about whether the update is partial or whole-document. For a write tool this is helpful but not fully transparent.

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 short sentences, no filler, with the core effect stated first and the failure/precondition rule immediately after. Nothing repeats the title or the schema.

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?

Annotations cover the safety profile and there is no output schema, so the description need not explain returns. It covers ownership preconditions and the rollback path, which is the hard part; the remaining gap is partial-update semantics for the four optional content fields.

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 0%, so the description carries the burden and only partly meets it: it explains rollback_to_version as restoring an earlier version as a new audited version, which is genuine meaning beyond the bare integer. However, id, body, title, and description get no semantics — most importantly whether omitting body/title replaces or preserves existing content.

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?

States a specific verb and effect ('Write a new version of a skill you own') plus the non-obvious invariant ('never mutates a prior version'), and names the sibling it is not (fork_skill). An agent can distinguish it from fork_skill, create_skill, and delete_skill without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit exclusion with a remedy: 'Fails on a skill you do not own — call fork_skill first to get an editable copy.' It also names a conditional mode (rollback_to_version) so the agent knows a second path exists through this same tool rather than a separate one.

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.