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

Annotations already establish readOnlyHint=true, destructiveHint=false and openWorldHint=true, so safety is covered. The description adds real domain context beyond the annotations: this reports draft-vs-live delta and explicitly includes merge conflicts, which tells the agent to expect conflict data in the result. It stops short of describing result structure or whether unpublished/deleted entities are included.

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?

A single tight sentence with zero padding and the key qualifier ('would go live on the next publish') front-loaded. It reads as a noun phrase rather than a declarative statement of what the tool does, which slightly weakens the lead.

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?

With five optional parameters, no required args, and no output schema, the description should indicate what the result contains (sections, rows, change types). It states the subject of the report but not its shape, leaving the agent to rely on the 'detail' enum to guess the return format.

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 description coverage is 100%, and each parameter (detail, folder, language, container, workspace) is documented in-schema with defaults and enum meanings. The description adds nothing about parameters, so the baseline 3 applies — the schema does all the work.

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 names a specific resource state — changes in the workspace draft that would go live on the next publish — which is clearly distinct from gtm_versions (published versions), gtm_audit, and the mutation siblings. It never names those siblings, however, so differentiation is left to inference rather than stated.

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?

Usage is only implied: the phrase 'would go live on the next publish' suggests a pre-publish review use case, but there is no explicit when-to-use, no exclusion ('do not use this for published versions — see gtm_versions'), and no prerequisite about choosing a container/workspace.

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