Query advisor

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

Annotations only declare readOnlyHint=true, so the description carries most of the burden, and it delivers: it discloses that every distinct query is EXPLAINed (compiled, not run), that weighting is by query runtime, and that it has a UI side effect of opening the Query History app on its Advisor tab. It does not mention cost/latency or caching behavior for the expensive compile pass.

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 deliverable, then the mechanism, then the browser_url usage note. Three tight sentences with no filler; the output-formatting instruction is slightly operational but genuinely useful.

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 exists, and the description compensates by naming the key return value (browser_url) and its intended use, plus the analysis method. The only real gap is the undocumented refresh parameter and any note that the first run is costly.

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?

The single parameter 'refresh' has 0% schema description coverage and is never mentioned in the description. Whether it forces recomputation versus returning a cached advisor report is left entirely to inference, which matters given the described expense of EXPLAINing all history.

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+resource (recommend table design changes from query history) and enumerates the concrete outputs: SORT KEY, SHARD KEY, reference-table candidates, indexes, missing statistics, workload issues. An agent can tell what it produces, though it never explicitly distinguishes itself from the sibling query_history_advisor.

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?

It describes scope ('the whole query history') but gives no when-to-use guidance, no prerequisites, and no direction on choosing it over the many sibling advisor/tuning tools (query_history_advisor, query_history_tuning, query_history_trends). The only routing hint is that it opens the Advisor tab.

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