execute_sql

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so safety is covered structurally. The description adds genuinely new context: only ONE statement is allowed and the statement is committed (no rollback), plus the mandatory WHERE guard on UPDATE/DELETE, which tells the agent about irreversibility and bulk-write protection.

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 filler, with the core scope constraint ('one DML statement') front-loaded before the safety precondition. Nothing repeats the schema or annotations.

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 values need not be described, and annotations cover the destructiveness profile. What remains thin is parameter-level detail: with 0% schema coverage, the agent gets no guidance on parameter binding, statement dialect, or error/transaction handling beyond the commit semantics.

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% for all three parameters, so the description must carry the load. It constrains what goes in `sql` (a single DML statement) and hints at `database` (must be a write-enabled alias), but the `params` binding parameter is never mentioned and no format/syntax or placeholder convention is given for the SQL string.

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 (commit/execute), resource (one DML statement), and scope constraint (single statement, write-enabled alias). It implicitly separates itself from read-only query_sql and from multi-statement execute_transaction, but never names a sibling explicitly, so the routing signal is inferred rather than stated.

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 phrase 'one DML statement' plus 'write-enabled alias' implies when this tool is appropriate (single write against a writable database) and 'UPDATE/DELETE require WHERE' gives a hard precondition. However, no alternative tool is named and no when-not condition is spelled out, so usage is implied rather than directed.

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