execute_sql

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

With no annotations provided, the description carries the full burden. It discloses the read-only nature, row limit, and available tables. It does not mention error handling or idempotency, but the constraints are clearly stated. No contradictions with annotations.

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?

Three sentences: purpose, exclusion, constraints. Front-loaded with the most critical information. Every sentence contributes meaningfully, with no waste.

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?

Given no output schema, the description covers purpose, constraints, when to use, and table names. It could mention that only SELECT is supported (implied by 'aggregation ONLY'), but it is adequate for an agent to decide and invoke correctly.

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 baseline is 3. The description adds value by specifying the row limit and the list of available tables (message, member), which are not in the schema descriptions. This extra context justifies a 4.

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 the tool is for statistical aggregation only and clearly distinguishes from get_messages for fetching message content. It specifies the SQL operations allowed (COUNT, GROUP BY, SUM, AVG) and the available tables, leaving no ambiguity about its purpose.

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 provides clear guidance on when to use the tool (statistical aggregation) and when not to (fetching message content), and names the alternative tool get_messages. It also sets constraints like max 200 rows and lists available tables, making usage decisions easy.

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