ghl_clientportal_list_mobile_customization_revisions

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

The annotations declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, but the description begins 'side-effecting: opens/edits sandboxes and starts builds' and discusses editing/checkpointing. This directly contradicts the read-only annotation for this tool and would mislead an agent about its safety profile.

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 actual purpose is buried after a multi-sentence API preamble about sandbox edits, checkpoints, and 409 responses, none of which apply to listing revisions. For a one-parameter read tool, the description is bloated and not front-loaded.

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?

It does state useful return behavior: up to 50 revisions, newest first, marking the current one and the member-facing one. But the contradictory side-effecting preamble introduces confusion, and the essentials are present but clouded.

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 the single projectId parameter is already documented as 'The app's id.' The description adds no further meaning about projectId syntax, format, or selection beyond what the schema provides, so the baseline 3 is appropriate.

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 sentence 'List a phone app's saved revisions' gives a specific verb and resource, and the restore endpoint mention distinguishes it from the restore sibling. However, the opening API-level warning about side effects blurs what this specific tool does.

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?

It usefully says to use POST .../restore to return to a revision, which routes the agent to the alternative operation. It gives no explicit guidance on when to use this list versus related tools like get_app_customization, and the sandbox edit/checkpoint guidance is irrelevant to listing.

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