Manage Unity Catalog grants

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

Adds substantial context beyond the coarse annotations: per-action safety classification (get/get_effective READ_ONLY, grant WRITE, revoke DESTRUCTIVE), the requirement that grant/revoke echo the principal's before/after direct privileges in a plan, the ALL_PRIVILEGES gating via allow_all_privileges, and the 'account users' flag. This refines the global destructiveHint=true into actionable per-action behavior.

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?

Front-loads the scope and action semantics, then the behavioral/safety constraints. Dense but every clause carries distinct, non-redundant information (action semantics, gating rules, safety classification) with no filler.

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?

An output schema exists, so return-value explanation is unnecessary, and the description covers the confirmation/dry-run safety flow and privilege gating. It omits any mention of pagination behavior (page_size/page_token) or the inherited-vs-direct distinction for mutating actions, which is a minor gap for a 10-parameter tool.

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 coverage is 100%, so the baseline is 3. The description reinforces cross-parameter constraints (principal+privileges required for grant/revoke; ALL_PRIVILEGES rejected unless allow_all_privileges) but largely restates what the schema property descriptions already say, adding little new syntax or format detail.

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 set (show/grant/revoke) and resource (Unity Catalog privileges on any securable), and enumerates the securable types so an agent knows the blast radius. It clearly distinguishes its four internal actions (get vs get_effective vs grant vs revoke), which is the key ambiguity for this tool.

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?

Gives explicit when-to-use guidance for the internal actions (get for direct, get_effective for inherited, grant/revoke require principal+privileges) and the confirmation workflow. It does not, however, differentiate this tool from siblings like manage_uc_sharing, manage_uc_security_policies, or manage_uc_tags, leaving some routing to inference.

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