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

The description goes beyond the annotations by explaining that it is pattern-matching (no AI model), returns SQL without executing, supplies a confidence score, and that low confidence means the table was guessed. It also mentions 'tables_used' in the output, giving the agent a clear picture of the tool's behavior and output beyond the safe read-only, idempotent, non-destructive traits already annotated.

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 three sentences, each serving a purpose: the first states the core function and scope, the second explains the output and confidence, and the third gives usage guidance and alternatives. It is front-loaded with the main action and contains zero redundant text.

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 single-parameter tool with no output schema, the description is remarkably complete. It covers purpose, limitations, return format (SQL, confidence score, tables_used), execution next steps, and when to use a different approach. There is no need for additional context.

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?

With 100% schema description coverage, the baseline is 3, but the description adds meaningful constraints on the 'question' parameter by limiting it to simple questions (counts, averages, filtered selects on a named table). This helps the agent decide whether to invoke this tool or use an alternative, going beyond the schema's generic example.

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 translates a plain-language question into a candidate SQL query using pattern-matching against the live schema, with a specific verb and resource (text-to-SQL). It distinguishes itself from siblings by noting it does not execute the query and is for simple questions only, such as counts, averages, and filtered selects on a named 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 explicitly defines when to use this tool (simple questions like counts, averages, filtered selects) and when not to (complex questions), directing users to read scalix_db_schema and write SQL directly for complex cases. It also tells the agent to run the resulting SQL with scalix_db_query, providing clear alternatives and follow-up actions.

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