Skip to main content
Glama
@yawlabs/tailscale-mcp

@yawlabs/tailscale-mcp

by YawLabs

Update key

tailscale_update_key
Idempotent

Update an existing Tailscale key's description, scopes, tags, or federated identity settings; auth keys accept only description.

Instructions

Update an existing key. Supported fields depend on the key type: all key types accept 'description'; OAuth clients and federated identities additionally accept 'scopes' and 'tags'; federated identities additionally accept 'issuer', 'subject', 'audience', and 'customClaimRules'. For auth keys, pass only 'description' -- the Tailscale API will reject other fields.

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": {
      "keyId": "<keyId>"
    },
    "name": "tailscale_update_key"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagsNoUpdated ACL tags (must start with 'tag:')
keyIdYesThe key ID to update
issuerNo(federated only) Updated OIDC issuer URL
scopesNo(client/federated) Updated OAuth scopes
subjectNo(federated only) Updated subject claim pattern
audienceNo(federated only) Updated audience claim
descriptionNoUpdated description (max 50 chars, alphanumeric/hyphens/spaces)
customClaimRulesNo(federated only) Updated custom claim rules

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.23.1
    • addedInput schema / properties / keyId / minLength
      Added value: +1
  2. First observedv0.13.3

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already cover safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), so the bar is lower. The description still adds real behavioral value: the API rejects fields not valid for the key type, which is an error condition the agent cannot infer from annotations or schema. It stops short of describing what happens to unspecified fields or what a successful response contains.

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 purpose is stated in the first sentence, and the key-type field matrix follows immediately with no filler. The enumeration is dense but each clause carries a distinct constraint, so nothing feels padded, though the single-paragraph field list is harder to scan than a short structured breakdown would be.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 8 parameters including a nested object, one required field, and no output schema, the definition supplies exactly what's needed to call it correctly: which fields are valid per key type and where the API will hard-fail. Combined with annotations that already declare it idempotent and non-destructive, an agent has enough to invoke this without trial and error.

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. The description goes beyond the schema by mapping parameters to key types as a group and by stating that 'tags' only apply to OAuth clients and federated identities, a restriction the schema's tags entry does not express. The federated-only annotations on issuer/subject/audience/customClaimRules are largely repeated from the schema, which caps the gain.

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 definition opens with a specific verb and resource ('Update an existing key'), which is unambiguous against create_key, get_key, and delete_key. It does not explicitly differentiate itself from tailscale_update_device_key, but the field enumeration (scopes, tags, issuer, subject, audience) makes clear this targets auth/OAuth/federated trust credentials rather than device keys.

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 conditional guidance keyed on key type: all types accept 'description', OAuth clients and federated identities also take 'scopes'/'tags', federated identities take the OIDC claims. It even states the negative condition for auth keys ('pass only description -- the API will reject other fields'). What's missing is explicit routing versus siblings or any prerequisite/permission context, keeping it at 4 rather than 5.

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

Deploy Server

Other Tools