ghl_clientportal_create_project

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

Adds value beyond annotations: required OAuth scope (clientportal-ai.write), the v3 Version header, and the meaning of a 409 response. The "side-effecting" framing is consistent with readOnlyHint=false and openWorldHint=true, so no contradiction — but the 409/checkpoint guidance belongs to sandbox tools, not this endpoint, which dilutes the disclosure.

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 first three sentences are API-family boilerplate about opening/editing sandboxes and checkpointing, none of which this tool does, and they are front-loaded ahead of the actual purpose. The remainder (purpose, next step, endpoint, scope) is dense and earns its place.

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?

Covers endpoint, version header, auth scope, and the follow-on build step, which is enough for an agent to invoke and sequence the call. With no output schema, it would help to say what the response yields (project id / initial sandbox status) so the agent knows what to pass to agent-runs.

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 all body fields (prompt, appMode, templateId, hostingMode, productTarget, deprecated targetModes) are already documented inline. The description adds nothing about field choices or defaults — its `externalAgent: true` note refers to a different endpoint, not a parameter here. Baseline 3 applies.

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 a specific verb+resource twice ("Create a project" / "Creates an app in the sub-account") and gives the concrete endpoint POST /ai-builder-api/projects, so it is distinguishable from ghl_clientportal_update_project and ghl_clientportal_list_projects. It does not explicitly name those siblings, keeping it below a 5.

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?

Gives real sequencing guidance: after creation, start the first build via `POST .../agent-runs`, and send `externalAgent: true` when using a sub-account token. It does not state when to prefer update_project or list_projects instead, and the opening paragraph's sandbox-editing/checkpoint rules apply to sibling tools, not to this create call.

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