workload_tune

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

readOnlyHint=true is consistent with a recommendation-only tool, and the description usefully signals the output kinds (EXPLAIN, table design), so the agent knows nothing is mutated. It still omits whether the statement is executed, what auth or cost is involved, and whether the returned advice is heuristic or executed against the cluster.

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?

A single front-loaded sentence with no padding. It is efficient, though the parenthetical and the vague 'as for a query in the history' clause are doing less work than their word count suggests.

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 a four-parameter tool with no output schema and no parameter documentation anywhere, the description is too thin: it never defines the optional inputs, the expected output shape, or how this differs from the many adjacent tuning and workload 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 0% for four parameters, so the description carries the burden. 'One workload statement' implies the sql parameter, and 'as for a query in the history' loosely gestures at historical metrics like rows and p50_ms, but neither is named and database is entirely unexplained.

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 names a deliverable (tuning recommendations) and a scope (one workload statement) with EXPLAIN and table design called out, so the general purpose is discernible. However, the trailing phrase 'as for a query in the history' is ambiguous and it never distinguishes this from near siblings like query_history_tuning, query_advisor_report, or workload_test_statement.

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?

There is no explicit when-to-use guidance, no prerequisites, and no routing to alternatives despite a crowded workload_*/query_history_* sibling set. The only hint is the implicit 'one statement' scoping, which the agent must infer.

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