query_history_advisor

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

readOnlyHint=true already declares the safety profile, so the bar is lower. The description usefully adds that it EXPLAINs every distinct query 'without running it', clarifying it does not execute the workload. It does not, however, disclose the cost/time implications of EXPLAINing an entire history or any caching behavior, which matters for this kind of workload-wide analysis.

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 tight sentences with the purpose front-loaded and the enumerated outputs kept compact. The parenthetical '(without running it)' is load-bearing, not filler. Nothing redundant.

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 tool with no output schema, the description adequately conveys the category of returned advice but says nothing about the refresh parameter, result format, or whether the analysis is expensive/long-running. Adequate for the core purpose, incomplete around parameters and operational cost.

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% and the single parameter (refresh, default false) is not addressed anywhere in the description. The description therefore leaves the agent to infer the meaning and effect of refresh entirely from its name, failing to compensate for the coverage gap.

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 output (table-design advice) and enumerates the covered artifact types — sort keys, shard keys, reference tables, indexes, statistics, workload findings — plus the source scope (whole query history). An agent can tell what it produces, though it does not name or distinguish itself from likely-overlapping siblings like query_history_tuning or query_advisor_report.

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 never states when to choose this tool over the many adjacent siblings (query_history_tuning, query_advisor_report, query_history_assistant). There are no conditions, prerequisite statements, or exclusions — only an implicit sense that it is an advisory/analysis tool.

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