register_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. It does not say whether this is a mutation with persistent side effects, what permissions are needed, whether registration is idempotent, or what happens on syntax errors — meaningful gaps for a write operation with zero annotation coverage.

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?

A single front-loaded sentence with the action first and the supported statement forms immediately after. No filler, though the trailing '...' is slightly vague.

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 mutation tool with no annotations, no output schema, and an undocumented sole parameter, the description is thin: it does not describe the return value, success/failure signals, or side effects of registering a source or caching a table.

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 0% for the single 'sql' parameter, so the description must compensate. It does add value by specifying the accepted statement forms (CREATE LIGHTNING with REST/FILESTORE/DATABASE, or CACHE TABLE), but gives no syntax example, required clauses, or handling of the optional-looking ellipsis.

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 ('Register') and resource ('a new data source in Zetaris'), and clarifies two supported modes: CREATE LIGHTNING (REST/FILESTORE/DATABASE) or CACHE TABLE. This is clearly distinguishable from read-oriented siblings like list_tables and describe_table.

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 implies when to use it (when you want to register a source or cache a table) by naming the DDL forms, but gives no explicit when-not guidance or differentiation from run_query, which could plausibly also execute SQL. The selection logic against the sibling is left to inference.

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