ghl_clientportal_cli_get_project_context

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

The description adds substantial context beyond the annotations: 409 conflict semantics, the sandbox.status prerequisite, stack-dependent code layout (mobile files under `apps/mobile/app-extensions/`, registered via `POST .../sandbox/extension-routes`), and the required clientportal-ai.write scope. However, it explicitly calls the tool 'side-effecting' and says it 'opens the app's sandbox', which conflicts with the declared readOnlyHint=true — an agent trusting the annotation could invoke it in a context where environment mutation is unacceptable.

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?

Purpose is front-loaded in the second line and the operational caveats follow in priority order. The API-family preamble and the endpoint/version/OAuth footer are boilerplate, and 'opens/edits sandboxes' is restated when the sandbox is described again, but overall the text is dense with usable information rather than padded.

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 does describe what comes back (the stack, which decides how code is written, plus the kernel bundle) and explains the mobile-vs-web branching that determines where files live. It stops short of describing the response shape or what a `react_native_app_kernel_v1` kernel bundle contains, which would matter without an output schema.

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?

Only one parameter, `projectId`, and schema description coverage is 100% with an example and a `^prj_[A-Za-z0-9]+$` pattern, so the schema fully carries the load. The description adds nothing about the identifier beyond what the schema states, which is the expected baseline here.

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 and resource: 'Read an app's stack and open its sandbox for editing', and elaborates that it returns the stack, the kernel bundle, and opens the sandbox. An agent can distinguish it from the sandbox_view / sandbox_edit / sandbox_checkpoint siblings because this is the entry point that reads stack metadata and provisions the sandbox.

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?

Provides real operating conditions: edit only once `sandbox.status` is `ready`, checkpoint after edits and before starting a build, and 409 means a cloud build owns the sandbox. It does not explicitly route to alternatives (sandbox_view, sandbox_edit, sandbox_checkpoint) by name, so it falls short of a 5.

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