Skip to main content
Glama
debanjanbasu

grr

by debanjanbasu
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

analyticsadmin.properties.googleAdsLinks.delete

Removes a Google Ads link from an Analytics property, detaching the linked Ads account; the deletion is irreversible unless an undo flow is documented.

Instructions

Deletes a GoogleAdsLink on a property [HTTP DELETE] — removes the resource; irreversible unless the API documents a trash/undo flow; refused under --readonly safety profiles. Returns the post-delete resource state (or empty) as JSON — request bodies are built from the typed parameters (typed flags win over the params map), or read whole from body_file Siblings over the same resource: create, list, patch.

Input Schema

NameRequiredDescriptionDefault
nameYes[URL path segment] Required. Example format: properties/1234/googleAdsLinks/5678
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.
body_fileNoRead the request body from this file ('-' for stdin) instead of building one from the parameters.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / name / description
      Previous value: -"Required. Example format: properties/1234/googleAdsLinks/5678"New value: +"[URL path segment] Required. Example format: properties/1234/googleAdsLinks/5678"
    • addedInput schema / properties / name / pattern
      Added value: +"^properties/[^/]+/googleAdsLinks/[^/]+$"
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "type": "object"
+}
  2. First observed

TDQS

A4.2/5.0
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 does well: it discloses irreversibility, readonly-profile refusal, that a body may be built from typed params or a file, and what is returned (post-delete resource state or empty). It omits any permission/scope requirements for the delete, a notable gap for a destructive mutation.

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?

Front-loads the core action and destructiveness, then tacks on return format and sibling list in a tight, information-dense block with no wasted sentences.

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?

Return values are covered by the output schema and the description additionally notes the post-delete state; safety behavior and body-building are explained. Only the permission/auth requirements for a destructive delete are unaddressed.

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 parameters are already documented; the description only restates the typed-vs-params precedence and body_file behavior. It adds no new semantics (e.g., path format for name) beyond the schema, matching the baseline 3.

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 (Deletes) and resource (GoogleAdsLink on a property), plus tags it HTTP DELETE. It also names the sibling operations over the same resource (create, list, patch), so the agent can distinguish it without inspecting other schemas.

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?

Clearly frames the destructive action and the --readonly safety-profile context in which it is refused, giving an agent concrete conditions for when it will fail. It lists the sibling operations but does not explicitly contrast when to delete vs. patch (e.g., deactivate instead).

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