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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuinely new behavioral information beyond the annotations: the tool has two possible outcomes (rows returned, or a still-running indication), which tells the agent to expect a polling-style result rather than a guaranteed payload. It does not cover pagination, retention of results, or behavior for an unknown/expired query ID.

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?

A single front-loaded sentence with no filler; the alternate outcome is packed into a clause rather than a second sentence. Nothing could be removed without losing information.

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 one-parameter read tool with annotations covering the safety profile and no output schema, the description is sufficient: it names the input, the primary return (rows), and the non-success state. Only the linkage to run_query and result lifetime are missing, which are minor for this complexity.

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?

There is one parameter with 0% schema description coverage, so the schema contributes no meaning for query_id. The description partly compensates by identifying it as the ID of a slow query, but it does not say the ID comes from run_query, its format, or what happens with an unknown ID.

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 concrete verb and resource ('Get the rows of a slow query by its query ID') and clarifies the resource identity (query ID). It is clearly distinct from the write/list siblings and from run_query, though it never names run_query as the producer of the ID, so the relationship is inferred rather than stated.

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 phrase 'by its query ID' implies this is called after a query has been submitted, and the 'still running' clause implies polling, but neither the precondition (obtain ID from run_query) nor a when-not-to-use case is stated explicitly.

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