GTM versions

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds genuine context beyond that: the sort order (newest first), what each row contains, that the live version is marked, and an explicit statement that publishing is unavailable.

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?

Two tight sentences with no filler; the scope ('Read only: publishing is not offered') is stated up front rather than buried, and the returned-field parenthetical is compact.

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 no output schema, the description usefully enumerates the returned fields, and annotations carry the safety profile. For a two-parameter read tool this is close to complete, though it could say more about pagination/limit behavior and when this beats gtm_workspace_status.

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%, so both parameters (limit, client_id) are already documented in the schema, including the multi-client requirement. The description's 'the client's GTM container' only loosely corroborates client_id and adds nothing about the limit.

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?

States the resource (client's GTM container versions), the ordering (newest first), the fields returned (id, name, tag/trigger/variable counts), and that the live version is flagged. It is clearly distinguishable from get-style siblings like gtm_get_tag, though it never uses an explicit verb such as 'list' and does not name a sibling alternative.

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 — an agent infers it should call this to inspect version history or find the live version. The 'publishing is not offered' line sets a scope boundary but does not route the agent to an alternative tool (e.g. a plan/publish sibling), and no when-not conditions are given.

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