ghl_project_get_folder_users

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

Annotations already establish readOnly/idempotent/non-destructive, and the description adds real context beyond them: results come back as one merged `users` page with a `source` of `direct` | `inherited`, pagination applies to the combined list rather than per source, and no PII is returned. The large opening block about task batch-get RBAC, lexorank positions, and delete cascades belongs to other project tools and dilutes the behavioral signal for this one.

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 generic Project Management API boilerplate about the hierarchy, task batch-get RBAC filtering, opaque lexorank `position` values, recurring-task field naming, and delete cascades — none of which applies to listing folder users. The useful content is buried after that preamble instead of being 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?

There is no output schema, and the description does disclose the response envelope (a unified `users` page with a `source` discriminator) plus pagination semantics and the absence of PII, which is enough to call it correctly. It never says what fields a user object carries or whether the merged list is deduplicated when a user is both direct and inherited, leaving a real gap for a tool 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?

Schema description coverage is 100%, so the schema already documents skip, limit, folderId and the locationId/token nuance. The description only echoes that skip/limit page the merged list, which is a modest addition over the schema's own wording — baseline 3 is right when 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 operative line, 'Get Users With Folder Access / Lists users with access to the folder,' gives a specific verb and resource, and the folder scope distinguishes it from ghl_project_get_list_users and ghl_project_get_space_users in the sibling list. An agent can pick it without opening the 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 states the resource being enumerated and points at the paired revoke path (DELETE /projects/folders/{folderId}/users/{userId}), which tells the agent what this call pairs with. It stops short of explicitly contrasting against the space-level and list-level user tools, so the alternative routing is inferred rather than stated.

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