create_saved_query

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

With no annotations, the description carries the full burden of behavioral disclosure. It explicitly states the critical side-effect condition: 'No write occurs unless confirm is true,' which informs the agent about the safe preview mode and the actual write behavior. While it doesn't detail return values or error conditions, this is a substantial transparency improvement over typical create tools.

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 just two sentences, front-loading the main purpose and then adding the crucial confirm caveat. Every word earns its place, with no fluff or 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?

This is a complex tool with 9 parameters, 3 required, no output schema, and no annotations. The description is far too brief to cover the required context: what preview returns, how the saved query is stored, what extra_json and template_parameters do, and what happens on write. The agent is left with significant unknowns.

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% (no descriptions on the 9 parameters), so the description must compensate. It mentions 'confirm' indirectly but does not explain the key required parameters (db_id, label, sql) or optional ones like extra_json, template_parameters, schema, or catalog. The agent gets almost no guidance on what these values mean or how to use them.

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's core action: 'Preview or create a saved query.' The verb 'create' is specific to the resource 'saved query,' and 'preview' adds a secondary mode. This distinguishes it from siblings like update_saved_query, list_saved_queries, and execute_sql, which handle different operations.

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 usage when you need to preview or create a saved query, and the confirm flag provides a hint about the two modes. However, it does not explicitly contrast with alternatives like update_saved_query or explain when to prefer this over executing SQL directly. This is implied rather than explicit.

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