ghl_project_update_folder

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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true), yet the description adds genuinely non-obvious behavior: OAuth scope projects/workspace.write, the add-only grant semantics, and the fact that existing direct grants persist but stop gating access when the folder is made public. The delete-cascade warning and lexorank note are accurate but largely irrelevant to a folder update, diluting the value slightly.

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?

Roughly half the text is API-wide boilerplate about task batch-get RBAC filtering, embedded subtasks, lexorank `position`, recurring-task field names, and task search — none of which applies to updating a folder. The tool-specific content is buried after that preamble, so the description is poorly front-loaded for its actual subject.

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 3-parameter PATCH with full schema coverage and existing annotations, the definition supplies the endpoint, version header, OAuth scope, and privacy side effects — enough to call it correctly. Only a note on what the update returns is missing, and no output schema exists to cover that.

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 nested body already documents `color` (full enum list), `userIds` (add-only), and `isPrivate` verbatim. The description restates the same facts rather than adding new meaning, so this is a baseline-3 case where the schema does the heavy lifting.

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 'Update Folder' section states a specific verb and resource with the exact fields it touches (name, color, privacy) and pins the endpoint to PATCH /projects/folders/{folderId}, which cleanly separates it from ghl_project_update_space and ghl_project_update_list. The hierarchy preamble reinforces where folders sit (spaces -> folders -> lists -> tasks), so an agent can place the operation without opening a schema.

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 explains the key routing decision an agent would otherwise get wrong: `userIds` is add-only on this call, and revocation must go through `DELETE /projects/folders/{folderId}/users/{userId}` (i.e. ghl_project_delete_folder_user). It also clarifies the isPrivate:false path. It stops short of explicitly framing when to prefer this over other folder tools (get/delete), but the context is clear.

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