run_sql

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

No annotations are provided, so the description carries full burden. It discloses that the tool can execute DDL and queries, implying modification capabilities, but does not warn about destructive potential, required permissions, or side effects. This is a significant omission for a tool that can alter database state.

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 extremely concise with two sentences, no wasted words, and front-loads the core purpose. Every sentence serves a clear function.

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 the tool's complexity (executes arbitrary SQL, no output schema, no annotations), the description lacks critical context such as error behavior, result format details beyond markdown table, and safety warnings. It is minimally adequate but not complete.

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 100%, so baseline is 3. The description mentions SQL execution and markdown table output but adds no additional meaning beyond the schema's parameter descriptions (e.g., bind parameters are well-documented 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?

The description clearly states the tool executes SQL (DDL or queries) against a provisioned project, and specifies the output format as a markdown table. This distinguishes it from sibling tools like rest_query (REST API) and get_schema (schema retrieval).

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 for executing raw SQL on a provisioned project, but provides no explicit guidance on when to use or avoid this tool, nor does it mention alternatives like get_schema for read-only schema queries or rest_query for API calls.

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