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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety baseline is covered. The description adds real value beyond that: writes are rejected by an enforced read-only role, and queries must carry an explicit LIMIT. It does not describe result size limits or return shape, so it stops short of 5.

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?

Two sentences, front-loaded with the core action and the routing condition, with no filler. The safety and LIMIT constraints are compact and each clause earns its place.

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-string-parameter escape-hatch tool with no output schema, the description covers what it does, when to reach for it, its safety posture, and the LIMIT requirement. The only minor gap is the absence of any note on result format or row caps, which the annotations and schema cannot supply.

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% and the schema already states 'a single SELECT or WITH statement, read-only'. The description goes slightly beyond by adding the mandatory LIMIT convention and concrete query shapes (GROUP BY, distinct counts) that clarify what belongs in the sql string.

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 and resource: an arbitrary READ-ONLY SQL query against the tenant database. It enumerates the use cases (aggregations, joins, GROUP BY, distinct counts) and expressly positions itself against the curated find_* family, so an agent can tell it apart from search-style siblings without reading schemas.

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?

Explicitly gives the selecting condition: 'when no curated find_* tool fits', naming the alternative family to prefer. It falls short of a 5 because it does not disambiguate from other SQL-capable siblings like run_sql or dispatch_query, which an agent could plausibly confuse with this one.

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