Skip to main content
Glama

update_secret_reference

DestructiveIdempotent

Update selected fields on a secret reference, including auth config merged into existing manager settings and workspace access mappings replaced.

Instructions

Update at least one selected field on a Secret Reference. auth_config is merged into the existing manager-specific configuration. allowed_workspaces replaces all workspace mappings and sets allow_all_workspaces=false; allow_all_workspaces=true removes workspace-specific mappings. Credential values are sent to Portkey and exposed to the MCP transcript.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesSecret Reference UUID or slug
nameNoNew human-readable name
tagsNoReplacement string key-value tags, or null to clear them
secret_keyNoNew key within a structured secret, or null to use the whole value
auth_configNoProvide at least one changed authentication field to merge into the existing configuration; choose one AWS, Azure, or HashiCorp field family and do not mix families
descriptionNoNew description, or null to clear it
secret_pathNoNew path of the secret in the external secret manager
allowed_workspacesNoReplacement list of workspace UUIDs or slugs allowed to use this reference; supplying it sets allow_all_workspaces=false
allow_all_workspacesNoWhether every workspace may use this reference; cannot be true with allowed_workspaces

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
okYesWhether the tool call succeeded and returned structured data
dataNoStructured success payload when ok is true
errorNoStructured error payload when ok is false

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.12.2
    • changedInput schema / properties / auth_config / anyOf
      Previous value: -[
      -  {
      -    "additionalProperties": false,
      -    "properties": {
      -      "aws_access_key_id": {
      -        "description": "AWS access key ID; required when aws_auth_type is accessKey",
      -        "minLength": 1,
      -        "type": "string"
      -      },
      -      "aws_auth_type": {
      -        "description": "AWS authentication mode: accessKey uses a key pair, assumedRole uses an IAM role, and serviceRole uses the runtime workload identity",
      -        "enum": [
      -          "accessKey",
      -          "assumedRole",
      -          "serviceRole"
      -        ],
      -        "type": "string"
      -      },
      -      "aws_external_id": {
      -        "anyOf": [
      -          {
      -            "type": "string"
      -          },
      -          {
      -            "type": "null"
      -          }
      -        ],
      -        "description": "Optional external ID required by the target IAM role"
      -      },
      -      "aws_region": {
      -        "description": "AWS region containing the secret, for example us-east-1",
      -        "type": "string"
      -      },
      -      "aws_role_arn": {
      -        "description": "IAM role ARN to assume; required when aws_auth_type is assumedRole",
      -        "minLength": 1,
      -        "type": "string"
      -      },
      -      "aws_secret_access_key": {
      -        "description": "AWS secret access key; required when aws_auth_type is accessKey and exposed to the MCP transcript",
      -        "minLength": 1,
      -        "type": "string"
      -      }
      -    },
      -    "type": "object"
      -  },
      -  {
      -    "additionalProperties": false,
      -    "properties": {
      -      "azure_auth_mode": {
      -        "description": "Azure authentication mode: entra uses a client secret, managed uses managed identity, and default uses the runtime credential chain",
      -        "enum": [
      -          "entra",
      -          "managed",
      -          "default"
      -        ],
      -        "type": "string"
      -      },
      -      "azure_entra_client_id": {
      -        "description": "Microsoft Entra application client ID; required for entra authentication",
      -        "minLength": 1,
      -        "type": "string"
      -      },
      -      "azure_entra_client_secret": {
      -        "description": "Microsoft Entra client secret; required for entra authentication and exposed to the MCP transcript",
      -        "minLength": 1,
      -        "type": "string"
      -      },
      -      "azure_entra_tenant_id": {
      -        "description": "Microsoft Entra tenant ID; required for entra authentication",
      -        "minLength": 1,
      -        "type": "string"
      -      },
      -      "azure_managed_client_id": {
      -        "description": "Optional client ID of a user-assigned managed identity; omit for the system-assigned identity",
      -        "type": "string"
      -      },
      -      "azure_vault_url": {
      -        "description": "Azure Key Vault URL, for example https://example.vault.azure.net",
      -        "format": "uri",
      -        "type": "string"
      -      }
      -    },
      -    "type": "object"
      -  },
      -  {
      -    "additionalProperties": false,
      -    "properties": {
      -      "vault_addr": {
      -        "description": "Base URL of the HashiCorp Vault server",
      -        "format": "uri",
      -        "type": "string"
      -      },
      -      "vault_auth_type": {
      -        "description": "HashiCorp Vault authentication mode: token, AppRole, or Kubernetes",
      -        "enum": [
      -          "token",
      -          "approle",
      -          "kubernetes"
      -        ],
      -        "type": "string"
      -      },
      -      "vault_namespace": {
      -        "description": "Optional HashiCorp Vault Enterprise namespace",
      -        "type": "string"
      -      },
      -      "vault_role": {
      -        "description": "HashiCorp Vault Kubernetes auth role name",
      -        "minLength": 1,
      -        "type": "string"
      -      },
      -      "vault_role_id": {
      -        "description": "HashiCorp Vault AppRole role ID; required for approle authentication",
      -        "minLength": 1,
      -        "type": "string"
      -      },
      -      "vault_secret_id": {
      -        "description": "HashiCorp Vault AppRole secret ID; required for approle authentication and exposed to the MCP transcript",
      -        "minLength": 1,
      -        "type": "string"
      -      },
      -      "vault_token": {
      -        "description": "HashiCorp Vault token; required for token authentication and exposed to the MCP transcript",
      -        "minLength": 1,
      -        "type": "string"
      -      }
      -    },
      -    "type": "object"
      -  }
      -]New value: +[
      +  {
      +    "additionalProperties": false,
      +    "properties": {
      +      "aws_access_key_id": {
      +        "description": "AWS access key ID; required when aws_auth_type is accessKey",
      +        "minLength": 1,
      +        "type": "string"
      +      },
      +      "aws_auth_type": {
      +        "description": "AWS authentication mode: accessKey uses a key pair, assumedRole uses an IAM role, and serviceRole uses the runtime workload identity",
      +        "enum": [
      +          "accessKey",
      +          "assumedRole",
      +          "serviceRole"
      +        ],
      +        "type": "string"
      +      },
      +      "aws_external_id": {
      +        "description": "Optional external ID required by the target IAM role",
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "aws_region": {
      +        "description": "AWS region containing the secret, for example us-east-1",
      +        "type": "string"
      +      },
      +      "aws_role_arn": {
      +        "description": "IAM role ARN to assume; required when aws_auth_type is assumedRole",
      +        "minLength": 1,
      +        "type": "string"
      +      },
      +      "aws_secret_access_key": {
      +        "description": "AWS secret access key; required when aws_auth_type is accessKey and exposed to the MCP transcript",
      +        "minLength": 1,
      +        "type": "string"
      +      }
      +    },
      +    "type": "object"
      +  },
      +  {
      +    "additionalProperties": false,
      +    "properties": {
      +      "azure_auth_mode": {
      +        "description": "Azure authentication mode: entra uses a client secret, managed uses managed identity, and default uses the runtime credential chain",
      +        "enum": [
      +          "entra",
      +          "managed",
      +          "default"
      +        ],
      +        "type": "string"
      +      },
      +      "azure_entra_client_id": {
      +        "description": "Microsoft Entra application client ID; required for entra authentication",
      +        "minLength": 1,
      +        "type": "string"
      +      },
      +      "azure_entra_client_secret": {
      +        "description": "Microsoft Entra client secret; required for entra authentication and exposed to the MCP transcript",
      +        "minLength": 1,
      +        "type": "string"
      +      },
      +      "azure_entra_tenant_id": {
      +        "description": "Microsoft Entra tenant ID; required for entra authentication",
      +        "minLength": 1,
      +        "type": "string"
      +      },
      +      "azure_managed_client_id": {
      +        "description": "Optional client ID of a user-assigned managed identity; omit for the system-assigned identity",
      +        "type": "string"
      +      },
      +      "azure_vault_url": {
      +        "description": "Azure Key Vault URL, for example https://example.vault.azure.net",
      +        "format": "uri",
      +        "type": "string"
      +      }
      +    },
      +    "type": "object"
      +  },
      +  {
      +    "additionalProperties": false,
      +    "properties": {
      +      "vault_addr": {
      +        "description": "Base URL of the HashiCorp Vault server",
      +        "format": "uri",
      +        "type": "string"
      +      },
      +      "vault_auth_type": {
      +        "description": "HashiCorp Vault authentication mode: token, AppRole, or Kubernetes",
      +        "enum": [
      +          "token",
      +          "approle",
      +          "kubernetes"
      +        ],
      +        "type": "string"
      +      },
      +      "vault_namespace": {
      +        "description": "Optional HashiCorp Vault Enterprise namespace",
      +        "type": "string"
      +      },
      +      "vault_role": {
      +        "description": "HashiCorp Vault Kubernetes auth role name",
      +        "minLength": 1,
      +        "type": "string"
      +      },
      +      "vault_role_id": {
      +        "description": "HashiCorp Vault AppRole role ID; required for approle authentication",
      +        "minLength": 1,
      +        "type": "string"
      +      },
      +      "vault_secret_id": {
      +        "description": "HashiCorp Vault AppRole secret ID; required for approle authentication and exposed to the MCP transcript",
      +        "minLength": 1,
      +        "type": "string"
      +      },
      +      "vault_token": {
      +        "description": "HashiCorp Vault token; required for token authentication and exposed to the MCP transcript",
      +        "minLength": 1,
      +        "type": "string"
      +      }
      +    },
      +    "type": "object"
      +  }
      +]
  2. Addedv0.5.0

TDQS

A3.9/5.0
Behavior5/5

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

Goes well beyond the annotations (which only flag destructive/idempotent/openWorld) by disclosing the merge behavior for auth_config, the side effect that allowed_workspaces sets allow_all_workspaces=false and vice versa, and the security-critical fact that credential values are sent to Portkey and exposed to the MCP transcript.

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?

Three tight sentences, front-loaded with the core action followed by the two highest-risk behaviors. Every sentence carries distinct information (merge, workspace side effect, credential exposure) with no filler, though it could be organized with slightly clearer separation.

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 present, return values need not be described, and the description covers the mutation semantics, side effects, and credential exposure needed to call it safely. Minor gap: no explicit guidance on partial-update expectations for optional fields beyond auth_config.

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 the schema already documents each parameter, including the allowed_workspaces/allow_all_workspaces interaction. The description repeats the merge and workspace-replacement semantics rather than adding new format or constraint detail, matching the baseline 3 for high-coverage schemas.

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+resource ('Update ... a Secret Reference') and adds the partial-update semantic ('at least one selected field'), so an agent knows this is a mutation on an existing reference. It does not explicitly distinguish itself from create_secret_reference/delete_secret_reference beyond the tool name, keeping it short of a 5.

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

Usage Guidelines3/5

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

Usage is implied by the merge/replace semantics ('auth_config is merged', 'allowed_workspaces replaces all workspace mappings'), which tells the agent what effect a call has. There is no explicit statement of when to prefer this tool over rotate_api_key, create_secret_reference, or get_secret_reference, and no exclusions.

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