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

Annotations already declare readOnlyHint=true, so safety is covered; the description adds genuinely useful behavior beyond that: the alias whitelist, rejection of physical table names, and workspace scoping of results. It stops short of disclosing row limits, timeouts, or result caps, which matter for an arbitrary SQL endpoint.

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?

Three sentences, front-loaded with the operation, then the hard constraint (allowed aliases), then the rejection rule and scoping. No filler and nothing repeated from annotations.

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 single-parameter SQL tool with no output schema, the description covers what an agent must know to construct a valid query. The remaining gap is the shape/limits of results (row caps, pagination), which is a minor omission since output is query-dependent.

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?

With one parameter at 100% schema coverage the baseline is 3, but the description adds meaning the schema lacks: the exact set of legal FROM aliases and the fact that physical table names will be rejected. The schema's example query is complemented rather than duplicated.

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 (run a read-only SQL query) and resource (key-verification analytics), plus the Unkey endpoint it maps to. This clearly separates it from the CRUD siblings (create/get/update/delete key, identity, api), none of which touch analytics.

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 concrete usage constraints — the query must target one of five named public aliases, physical default.* tables are rejected, and results are workspace-scoped. It does not need to route to a sibling since no other analytics tool exists, but it also doesn't state any limits on query complexity or result size.

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