execute_sql

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

No annotations at all, so the description carries the full burden. It never says whether writes/DDL are permitted or persist, what permissions are required, how errors surface, or what the result looks like. "Prefer read-only SELECT" hints at risk without quantifying it.

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?

Two short sentences, zero repetition, with the core action front-loaded. It is terse to the point of under-specification, but contains 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?

For an arbitrary-SQL execution tool with no annotations and no output schema, the description says almost nothing about security posture, mutability, result shape, or row-limit semantics. An agent could call it correctly mechanically, but not safely or predictably.

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%, so the description must compensate. It only implicitly maps "SQL statement" to the `sql` parameter and adds the dialect hint; `max_rows` (bounds 1–10000) is never mentioned, including what it caps or whether a default applies.

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 and resource ("Run a MongrelDB SQL statement") and names the query engine (DataFusion), so the agent knows this is the raw-SQL escape hatch. It does not explicitly contrast itself with structured siblings like list_tables or describe_table, leaving differentiation implicit.

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?

"Prefer read-only SELECT for exploration" implies a usage posture (exploration vs. mutation) but never states when to call this instead of list_tables/describe_table/semantic_search, nor any exclusions. Usage is inferable but not spelled out.

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