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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new context: execution happens inside a bounded read-only transaction and writes/DDL are rejected both by this endpoint and again by the server, which tells the agent failures are enforced rather than advisory.

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 tight sentences with the constraint front-loaded; the rejection notice and server-side re-check follow logically. The trailing 'POST .../database/query.' fragment is marginal value for an agent but not harmful.

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?

There is no output schema, so the description ideally would say something about result shape or row limits; 'bounded' gestures at limits without quantifying them. For a four-parameter, fully-required query tool with annotations covering safety, the rest of what an agent needs to call it correctly is present.

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 nominally 100%, but the schema descriptions are vacuous placeholders like 'sql (required)', so the description is doing real work by narrowing the sql parameter to SELECT/WITH/EXPLAIN. It adds nothing about the three identifier parameters or any row/pagination limits, so the baseline applies.

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) and resource (a statement against the environment database) and constrains the statement grammar to SELECT/WITH/EXPLAIN. An agent can distinguish it from a general write executor, but no sibling is named even though sql.execute and sql.explain exist and overlap heavily.

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 allowed statement types and the explicit rejection of writes and DDL imply when this tool is appropriate. However it never says when to prefer sql.execute or sql.explain instead, which is a real ambiguity given EXPLAIN is listed as valid here while a dedicated explain sibling exists.

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