ghl_clientportal_get_project

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

The leading line declares the API 'side-effecting: opens/edits sandboxes and starts builds' and advises checkpointing before builds, yet the annotations for this tool declare readOnlyHint=true, idempotentHint=true and destructiveHint=false. That is a direct contradiction an agent could act on (e.g. avoid calling it or add unnecessary checkpoint steps). The 409/sandbox-ownership note is likewise irrelevant to a project read, though the return-value summary and OAuth scope line do add real value.

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 most prominent text is two sentences of sandbox/build boilerplate irrelevant to this read tool, pushing the actual operation ('Get a project by id') into second position. The endpoint/version/scope footer is useful, but the description is not front-loaded on what this tool does.

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 with no output schema, the description does supply endpoint path, version header, OAuth scope and a summary of the returned app fields, which is adequate. It is undercut by the copy-pasted side-effecting preamble that gives a false picture of the operation's behavior.

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% and already documents projectId with a 'prj_...' pattern, so the description's 'by id' framing adds nothing beyond it. Baseline 3 applies since the schema carries the parameter semantics entirely.

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 core sentence 'Get a project by id' plus the enumeration of what is returned (status, publication state, preview/production URLs, latest run) states a specific verb and resource. It is clear enough to distinguish from list_projects and update_project, though it never names those siblings explicitly and the unrelated sandbox preamble dilutes the opening.

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 gives workflow advice for sandbox editing and build runs ('Edit a sandbox only once sandbox.status is ready; checkpoint after edits'), but none of that applies to a GET-by-id call and none of it says when to pick this tool over ghl_clientportal_cli_get_project_context, ghl_clientportal_get_app_customization, or ghl_clientportal_list_projects. Guidance is present but aimed at the wrong operation.

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