Skip to main content
Glama

tasks.tasks.patch

Partially update a Google Task using patch semantics, changing only supplied fields and returning the API response as JSON.

Instructions

Updates the specified task. This method supports patch semantics [HTTP PATCH] — updates the resource; refused under --readonly safety profiles. Returns the API's response resource as JSON — request body is a JSON Task object accepting assignmentInfo, completed, deleted, due, etag, hidden, id, kind and 9 more fields; pass it via params or whole via body_file Siblings over the same resource: clear, delete, get, insert, list, move, update.

Input Schema

NameRequiredDescriptionDefault
taskYes[URL path segment] Task identifier.
queryNoExtra KEY=VALUE query pairs for endpoints whose parameters Discovery does not describe.
paramsNoParameter map merged into the request; typed parameters win.
dry_runNoReturn the request that would be sent, without sending it.
tasklistYes[URL path segment] Task list identifier.
body_fileNoRead the request body from this file ('-' for stdin) instead of building one from the parameters. The body is a JSON Task object.
request_bodyNoRequest body of type Task: pass it via `params` (merged into the built body) or whole via `body_file`.

Output Schema

NameRequiredDescriptionDefault
idNo
dueNo
etagNo
kindNo
linksNo
notesNo
titleNo
hiddenNo
parentNo
statusNo
deletedNo
updatedNo
positionNo
selfLinkNo
completedNo
webViewLinkNo
assignmentInfoNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / body_file / description
      Previous value: -"Read the request body from this file ('-' for stdin) instead of building one from the parameters."New value: +"Read the request body from this file ('-' for stdin) instead of building one from the parameters. The body is a JSON Task object."
    • addedInput schema / properties / request_body
      Added value: +{
      +  "description": "Request body of type Task: pass it via `params` (merged into the built body) or whole via `body_file`.",
      +  "properties": {
      +    "assignmentInfo": {
      +      "properties": {
      +        "driveResourceInfo": {
      +          "properties": {
      +            "driveFileId": {
      +              "type": "string"
      +            },
      +            "resourceKey": {
      +              "type": "string"
      +            }
      +          },
      +          "type": "object"
      +        },
      +        "linkToTask": {
      +          "type": "string"
      +        },
      +        "spaceInfo": {
      +          "properties": {
      +            "space": {
      +              "type": "string"
      +            }
      +          },
      +          "type": "object"
      +        },
      +        "surfaceType": {
      +          "enum": [
      +            "CONTEXT_TYPE_UNSPECIFIED",
      +            "GMAIL",
      +            "DOCUMENT",
      +            "SPACE"
      +          ],
      +          "type": "string"
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "completed": {
      +      "type": "string"
      +    },
      +    "deleted": {
      +      "type": "boolean"
      +    },
      +    "due": {
      +      "type": "string"
      +    },
      +    "etag": {
      +      "type": "string"
      +    },
      +    "hidden": {
      +      "type": "boolean"
      +    },
      +    "id": {
      +      "type": "string"
      +    },
      +    "kind": {
      +      "type": "string"
      +    },
      +    "links": {
      +      "items": {
      +        "properties": {
      +          "description": {
      +            "type": "string"
      +          },
      +          "link": {
      +            "type": "string"
      +          },
      +          "type": {
      +            "type": "string"
      +          }
      +        },
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "notes": {
      +      "type": "string"
      +    },
      +    "parent": {
      +      "type": "string"
      +    },
      +    "position": {
      +      "type": "string"
      +    },
      +    "selfLink": {
      +      "type": "string"
      +    },
      +    "status": {
      +      "type": "string"
      +    },
      +    "title": {
      +      "type": "string"
      +    },
      +    "updated": {
      +      "type": "string"
      +    },
      +    "webViewLink": {
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
  2. Changed3 schema fields changed
    • changedInput schema / properties / task / description
      Previous value: -"Task identifier."New value: +"[URL path segment] Task identifier."
    • changedInput schema / properties / tasklist / description
      Previous value: -"Task list identifier."New value: +"[URL path segment] Task list identifier."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "assignmentInfo": {
      +      "properties": {
      +        "driveResourceInfo": {
      +          "properties": {
      +            "driveFileId": {
      +              "type": "string"
      +            },
      +            "resourceKey": {
      +              "type": "string"
      +            }
      +          },
      +          "type": "object"
      +        },
      +        "linkToTask": {
      +          "type": "string"
      +        },
      +        "spaceInfo": {
      +          "properties": {
      +            "space": {
      +              "type": "string"
      +            }
      +          },
      +          "type": "object"
      +        },
      +        "surfaceType": {
      +          "enum": [
      +            "CONTEXT_TYPE_UNSPECIFIED",
      +            "GMAIL",
      +            "DOCUMENT",
      +            "SPACE"
      +          ],
      +          "type": "string"
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "completed": {
      +      "type": "string"
      +    },
      +    "deleted": {
      +      "type": "boolean"
      +    },
      +    "due": {
      +      "type": "string"
      +    },
      +    "etag": {
      +      "type": "string"
      +    },
      +    "hidden": {
      +      "type": "boolean"
      +    },
      +    "id": {
      +      "type": "string"
      +    },
      +    "kind": {
      +      "type": "string"
      +    },
      +    "links": {
      +      "items": {
      +        "properties": {
      +          "description": {
      +            "type": "string"
      +          },
      +          "link": {
      +            "type": "string"
      +          },
      +          "type": {
      +            "type": "string"
      +          }
      +        },
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "notes": {
      +      "type": "string"
      +    },
      +    "parent": {
      +      "type": "string"
      +    },
      +    "position": {
      +      "type": "string"
      +    },
      +    "selfLink": {
      +      "type": "string"
      +    },
      +    "status": {
      +      "type": "string"
      +    },
      +    "title": {
      +      "type": "string"
      +    },
      +    "updated": {
      +      "type": "string"
      +    },
      +    "webViewLink": {
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
  3. First observed

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and mostly succeeds: it discloses the read-only safety-profile refusal, states that the API's response resource is returned, and explains the two body-passing routes (`params` merge vs `body_file`). It doesn't spell out that unspecified fields are left untouched under patch semantics or what permissions are required.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded, but the middle clause listing body fields plus 'and 9 more fields' is padding against a 100%-covered schema, and the em-dash chain makes it a dense run-on. It is informative but not every clause earns its place.

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?

An output schema exists so return values needn't be explained, and the description still notes a JSON response is returned. For a 7-parameter nested-body mutation tool, the remaining gap is the absence of patch-semantics detail (field clearing vs preservation) and permission requirements.

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 `task`, `tasklist`, `query`, `params`, `body_file`, `dry_run` and the nested request body. The description adds only the routing note that the body can be supplied via `params` or `body_file`, which the schema also states. Baseline 3 applies; the field enumeration ('assignmentInfo, completed, ... and 9 more') merely restates 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 ('Updates the specified task') and flags that it is HTTP PATCH rather than a full replace, which is the meaningful axis of differentiation from the sibling `tasks.tasks.update`. It enumerates siblings but doesn't explicitly say how patch differs from update beyond the PATCH tag.

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 one concrete when-not condition ('refused under --readonly safety profiles') and lists the sibling set over the same resource, so the agent knows the alternative space. It stops short of an explicit rule like 'use patch for partial edits, update for full replacement'.

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