refresh_catalog

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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds substantial value beyond them: latency ('can take seconds on a large schema'), the guarantee it never changes the database, and the failure contract where an unreachable database keeps the previous catalog in service.

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-loads what it does, then when to call it, then behavioral facts (no args, non-mutating, latency), then return shapes. Every sentence carries distinct information with no repetition.

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?

Covers the trigger, the cost, the safety profile, and both success and failure return shapes, so an agent has everything needed to decide and invoke correctly. Rich enough that even the healthy/stale distinction needed to time the call 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?

Zero parameters, so the baseline is 4; the description confirms 'takes no arguments', which removes any doubt about supplying input. There is no additional parameter meaning to convey.

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 ('Re-read the database structure... swap the index in') and enumerates exactly what it picks up (new tables, changed columns, changed grants). An agent can distinguish this from siblings like list_objects or health without opening the schema.

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 names the trigger conditions (after a migration or permission change, or when health reports a stale catalog) and adds an explicit when-not ('it is not needed before ordinary questions'). This is route-level guidance, not inference.

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