update_data_source

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does this exceptionally well, disclosing that omitted options are permanently removed, affected rows are silently reassigned with no signal, and that is_inline changes are unsupported. This is precisely the kind of destructive and surprising behavior an agent must know before calling.

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 lengthy but each sentence carries substantive guidance. It is front-loaded with the critical destructive warning, followed by the inline exception and a clear summary of what the tool does. The structure is slightly unconventional—the core purpose statement appears near the end—but the density and organization are strong enough that nothing feels wasted.

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 complex mutation tool with zero annotations and no output schema, this description is exceptionally complete. It covers destructive edge cases, prerequisite calls, unsupported operations, accepted payload modes, documentation references, and required arguments. An agent has everything needed to invoke the tool correctly and avoid irreversible mistakes.

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 100%, so the baseline is 3. The description adds meaningful semantics beyond the schema, especially for the properties parameter: it explains full-list semantics for select/status options, the silent reassignment behavior, and the safe procedure for adding an option by first calling get_database. This extra guidance justifies a score above baseline.

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 explicitly states that this tool updates a database's schema: renaming properties, adding/updating/removing property definitions, changing the title, and moving to/from trash. This is a specific verb+resource and clearly distinguishes it from sibling tools like update_database_entry or update_view.

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 description gives explicit usage context: 'Use after get_database', mandates reading the docs resource for modes and limitations, and warns that is_inline cannot be toggled on existing databases. It also explains the required parameters ('At least one of title, properties, or in_trash must be provided'), leaving little ambiguity about when and how to invoke the tool.

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