Review a GTM version before manual publishing

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

Annotations already cover readOnly, idempotent, and non-destructive behavior English, but the description adds meaningful behavioral context: it compares by stable entity IDs, includes modified fields, and explicitly says the server cannot publish. This goes beyond simply repeating the annotations and clarifies side-effect constraints.

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

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

The description is three short sentences, front-loaded with 'READ ONLY' and the core comparison purpose. Every sentence adds useful information: what it compares, how it compares, what it cannot do, and when to use it. There is no wasted wording.

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

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

For a single-parameter, read-only comparison tool, the description fully covers selection and invocation. It explains the operation, the comparison basis, the side-effect boundary ('cannot publish'), and the intended context ('before publishing'). No output schema is present, but the description's 'including modified fields' and 'full changes' sufficiently indicate what will be returned.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%; the single parameter versionPath is fully described with a pattern and format. The description adds the 'candidate version' semantic but does not need to explain the parameter further. Baseline 3 is appropriate because the schema carries the parameter documentation burden.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a clear verb ('Compare') and specific resources ('candidate version' vs 'live version'), and explains the comparison basis ('stable entity IDs and configuration', 'including modified fields'). This differentiates it from siblings like gtm_get_live_version, which likely just fetches the live version rather than diffing against a candidate.

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

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

The description explicitly frames this as a pre-publishing review step: 'Review full changes in Google Tag Manager before publishing there.' It also states what the tool does not do ('This server cannot publish'), which is a useful exclusion. However, it does not explicitly name alternative tools or conditions for choosing them, so it falls short of a 5.

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