who_can_access

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

Annotations only declare readOnlyHint=true; the description confirms 'Read-only' and adds substantive behavioral detail beyond that, notably which privileges are deliberately excluded (global admin privileges like CREATE USER/PROCESS and USAGE) and the fact that the lookup navigates to the Security view. That UI side effect is genuinely useful context an agent would not get from annotations alone.

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-loaded with the return set, then the 'how' semantics, then the exclusions. The arrow notation ('via role R ← group G') and nested quoting are a little dense, but every sentence carries information and nothing is padding.

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?

With no output schema and only two fully documented parameters, the description covers inputs, result content, matching semantics, exclusions, and the read-only/UI behavior. An agent has enough to call it correctly; only the relationship to sibling security tools is left unstated.

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 0%, so the description carries the parameter burden, and it does: database is an exact name match, table is optional and scoped to that database. It adds the 'exact' matching semantics that the schema's bare string type does not convey.

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 resource and scope: every user with privileges on a database (or one table), plus how they obtained them. An agent can tell this is a privilege-audit lookup rather than a generic query. It never names the closely related siblings (security_who, user_privileges, security_users), so it stops short of full differentiation.

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?

Usage is implied by the scope definition and the exclusion note, and 'Opens the Security view on this lookup' hints at the workflow it belongs to. However, there is no explicit when-to-use versus security_who or user_privileges, and no stated prerequisites such as requiring a connected session.

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