ghl_clientportal_cli_sandbox_view

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

Beyond the annotations it discloses real behavioral facts: the kernel's own files are readable, the writable boundary applies only to POST .../sandbox/edit, folder paths always list regardless of the `list` flag, and the required OAuth scope is clientportal-ai.readonly. The opening 'side-effecting: opens/edits sandboxes and starts builds' banner is inherited context and is mildly misleading for a read tool, though it is consistent with readOnlyHint=false rather than contradicting it.

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 description repeats itself ('Read a file ... or list a folder' followed by 'Reads one file of the app's code, or lists a folder's files and subfolders'), and the tool's actual purpose appears only after an unrelated banner about builds and 409s. The endpoint/version/scope footer is useful, but the content is 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?

For a two-parameter nested-body read tool with no output schema, the definition covers purpose, listing semantics, the readability boundary, endpoint, and auth scope. It stops short of describing what a successful response contains (file text vs. tree structure) or the error shape for a missing path, which an agent consuming the result would benefit from.

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 baseline is 3; the description still adds meaning by explaining that 'a folder path always lists,' which clarifies how the `list` flag interacts with the `path` value. Path is described only as 'the file or folder, relative to the workspace root' in the schema, with no extra guidance in the description.

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 second paragraph states a concrete verb+resource: 'Read a file in the app's sandbox, or list a folder,' and clarifies that 'A folder path always lists.' However, the actual purpose is buried after a family-level banner about side effects, builds, and 409s that does not describe this tool. Differentiation from siblings is implicit (it names the edit endpoint's writable boundary) but never names ghl_clientportal_cli_sandbox_search as the alternative for locating code.

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 gives one useful context cue — an agent reads files 'so an agent sees what is there before it edits' — plus the rule that a folder path always lists. But it never says when to use view versus sandbox_search or sandbox_get_project_context, and the checkpoint/ready guidance in the header concerns edit/build tools rather than this one, so routing between siblings is left to inference.

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