execute_dml

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

With no annotations the description carries the full burden and does so well: it discloses auto-commit semantics, the absence of a cross-call transaction boundary, one-statement-per-call enforcement, the row-count return, and how privilege failures surface (isError=true). It stops short of flagging irreversibility/rollback options, but the auto-commit statement implies 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?

Front-loaded with the core verb and target, then layered with commit semantics, call constraints, and return/error behavior. Slightly dense but every clause is load-bearing and there is 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?

No output schema, so the description correctly explains the return value (rows affected) and error channel (isError=true). Given a single required parameter, this is nearly complete; the only gap is routing guidance versus the preview/rollback sibling tools.

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% for the single 'sql' parameter, so the baseline is 3. The description reinforces the allowed statement types and the single-statement constraint, but adds no syntax or format detail beyond 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 (Execute) and resource (a single INSERT/UPDATE/DELETE/MERGE statement on existing tables), and constrains to one statement per call. This distinguishes it from run_query (reads), execute_dml_preview, and execute_dml_rollback_first 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?

Conveys the operating model (single statement, auto-commit, no cross-call transaction) which implies when it applies, but never names the obvious alternatives. Siblings execute_dml_preview and execute_dml_rollback_first exist and an agent gets no explicit rule for choosing between them.

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