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

Annotations already declare destructiveHint=true and openWorldHint=true, but the description adds critical operational context: the user-approval flow, automatic schema helper re-pull on DDL, default single-transaction wrapping, and a 90-second kill timeout. This is exactly the behavioral detail annotations cannot convey.

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 core purpose and statement types, then layers operational details. It is dense and somewhat long, but nearly every sentence earns its place by conveying approval, transaction, or timeout behavior.

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, the description itself closes the loop by explaining that schema-changing statements return the updated typed schema. Transaction handling, timeout, multi-DB selection, and approval are all covered, leaving no significant gaps for a high-risk write tool.

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 only 25% (just no_transaction documented), so the description must compensate. It explains `database` semantics (needed only for multi-database projects) and reinforces `no_transaction`, though `projectId` and the `query` string itself receive no explicit elaboration.

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+resource ('Run a WRITE SQL statement against the project's Postgres database') and enumerates the statement classes (CREATE/ALTER/INSERT/UPDATE/DELETE/DROP, migrations). The write framing clearly distinguishes it from the read sibling query_database.

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?

Explains exactly when to use it (write statements), when `database` is needed ('only if the project has more than one'), and when `no_transaction` applies (VACUUM, CREATE INDEX CONCURRENTLY). Also tells the agent a separate pull_database_schema call is unnecessary after schema changes.

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