ghl_project_delete_space_user

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

Annotations already declare destructiveHint=true, idempotentHint=true, readOnlyHint=false, and openWorldHint=true, so the safety profile is covered. The description adds real context beyond that: the exact effect (direct grant revocation, `isPrivate` untouched, inherited access preserved), the OAuth scope required (projects/workspace.write), and a caution that cascade behavior is undocumented so deletes should be treated as destructive.

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 the first two-thirds of the description is a generic PROJECT MANAGEMENT API preamble about hierarchy, RBAC-filtered batch-get, lexorank `position`, recurring task fields, and search sync — none of which bear on revoking a space member. The tool-specific content is buried after this noise, so the definition is neither front-loaded nor waste-free.

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 simple two-required-parameter DELETE endpoint with no output schema, the tool-specific portion covers what an agent needs: the effect, idempotency, what is and isn't modified, the endpoint/version, and the required OAuth scope. The unrelated family preamble doesn't add needed information but doesn't leave a critical gap in understanding the call itself.

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% — spaceId, userId, and the channel-specific locationId rules (required for APP channel, ignored for OAuth/PIT, not to be sent in path/body/headers) are all documented in the schema. The description adds no parameter-level meaning beyond that, so the 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?

The operative sentence names a specific verb and resource: 'Revokes a direct user grant on the space,' which correctly clarifies that the '_delete_space_user' name means revoking a membership grant, not deleting a user. It implicitly distinguishes direct grants from inherited ancestor access, though it never explicitly names the sibling tools (ghl_project_delete_space, ghl_project_delete_list_user) an agent might confuse it with.

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?

The description supplies useful scoping facts — idempotent when the grant is absent, does not change `isPrivate`, inherited access unchanged — which tell an agent what this call will and won't accomplish. However, it never states when to prefer this over alternatives such as removing access via ancestor/parent-level operations or the three sibling '*_delete_*_user' tools, so the choice between them remains inferred.

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