run_sql

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

With no annotations, the description carries the full burden and does well: it declares read-only scope, a default 200-row cap, a multi-second timeout, and a truncated flag. Gaps remain on error behavior and whether the cap is configurable, so it is not exhaustive.

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, front-loaded with the scope and return shape, then limits, then the prerequisite. Every sentence carries actionable information with no filler.

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?

An output schema exists, so return formatting need not be spelled out, and the description still concisely names the return pieces. Combined with read-only scope, limits, and the describe_schema prerequisite, an agent has nearly everything needed to call it safely.

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% and there is one undocumented parameter, but the description constrains it meaningfully: the query must be a read-only SELECT or WITH ... SELECT. That syntax constraint adds real meaning beyond the bare "Query" string in the schema.

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 (run) and resource (read-only SQLite SELECT or WITH ... SELECT) and names the exact return shape (columns, rows, truncated flag). An agent can distinguish this generic query tool from siblings like describe_schema and the canned sales_summary/refund_rate tools without opening any schema.

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?

Gives an explicit prerequisite ("Call describe_schema first if you haven't seen the tables") and a workflow preference ("Aggregate in SQL rather than pulling raw rows"). It stops short of naming when to prefer the prebuilt siblings (sales_summary, top_customers) over raw SQL, so no full when/when-not routing.

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