gtm_publish_version

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

With no annotations provided, the description bears the full disclosure burden. It does warn that this is PRIVILEGED and requires user approval, which is meaningful behavioral context. However, it does not disclose that publishing pushes content to production, is likely irreversible, or what the consequences of the mutation are — for a privileged production action, more disclosure is expected.

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 short sentences with zero fluff, and the core purpose is front-loaded before the privilege warning. Efficient and scannable, though the sparseness borders on under-specification for such a consequential operation.

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?

This is a privileged production mutation with no annotations, no output schema, and 5 params at 0% schema coverage — yet the description is only one clause plus a warning. Missing: irreversibility/consequences, the meaning of connection_id/session_token, prerequisites beyond 'prepared', and any return expectations. Given the tool's complexity and privilege level, this is materially incomplete.

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 0%, so the description must compensate; it adds nothing about any parameter. While account_id/container_id/version_id are self-explanatory, the optional connection_id and session_token are entirely opaque and undocumented in both schema and description. The description provides zero value beyond the schema field names.

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 specific verb and resource ('Publish a prepared GTM version to live') that clearly distinguishes it from siblings like gtm_create_version (which creates a draft) and gtm_get_version (which reads). The 'prepared' qualifier adds meaningful scope. Purpose is unambiguous and separable at a glance.

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 'only call after explicit user approval' gate is a real when-to-use constraint, but the description gives no guidance on how this tool differs from alternatives or when it should be chosen over gtm_create_version or the read-only list/get family. There is no exclusion statement or sibling reference, leaving the agent to infer positioning.

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