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

Annotations are sparse (readOnlyHint false, destructiveHint false), so the description carries the burden. It discloses that the helper is generated, warns against hand-editing, and explains the workflow for fixing loose types. It does not explicitly state whether it modifies the database, but it implies a side effect by writing a file. This adds meaningful context beyond annotations, though it could be more explicit about what files are written or if any DB changes occur.

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?

The description is long but every sentence adds value. It front-loads the core purpose, then gives usage context, then actionable advice about generated code. It is not bloated despite its length; it's efficient and well-structured for a tool with this complexity.

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?

Given there is no output schema and the tool involves multiple steps (introspection, helper generation, working with different SQL dialects), the description covers the key points: when to use, optional helper_name, and the pitfall of editing generated code. It does not detail the return value or file paths, but that's likely not critical for an agent's correct invocation. It's quite complete for its 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?

Schema description coverage is 0%, so the description must compensate. It explains helper_name clearly (generates helper for additional/external database) but does not elaborate on database or projectId. Given three parameters and only one explained, the description adds value but incomplete. Baseline for low coverage would require more, so a 3 is fair.

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?

The description clearly states the tool introspects the database and writes a typed schema helper, and specifies it matches the project's existing approach (kysely vs drizzle). It distinguishes itself from execute_sql by noting it's usually not needed after schema changes auto-pull. This is a specific verb+resource with clear differentiation from a key sibling.

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?

Explicit guidance is given: use it to manually refresh or with helper_name for additional databases, and avoid it after execute_sql since schema-changing statements re-pull automatically. This provides clear when-to-use and when-not-to-use instructions, exceeding simple context hints.

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