Impala Query Issues Summary

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

With no annotations, the description carries the entire burden. It does disclose meaningful behavior beyond the schema: classification thresholds (long, excessive memory, slow planning) and the normalization rule that recurring queries replace literals with '?'. It does not state that the operation is read-only or side-effect free, nor how heavy the scan over max_queries is, and the return shape is left to the output schema.

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?

The overview is front-loaded and the threshold parameters follow as a compact bullet-style list, so the reader can scan it quickly. Every sentence contributes, though the parameter block could be tightened or extended to cover the missing inputs.

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?

This is a 10-parameter analytical tool with no annotations and no schema descriptions, and the description documents only a third of them. The existence of an output schema reduces the need to describe return values, but the scoping and cost-control parameters (max_queries, hours, top) remain unexplained, which leaves the definition incomplete for correct invocation.

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 coverage is 0%, so the description has to compensate, but it only explains 3 of 10 parameters (slow_seconds, memory_gb_per_node, planning_seconds). The most consequential inputs, including the required `cluster` and the filters `hours`, `pool`, `user`, `top`, and the `max_queries` cap, receive no explanation, so their effect on results and cost is left to guesswork.

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 the resource (Impala query problems in a time window) and enumerates the specific content: long query counts, memory/OOM, spill, failures/planning problems, user and pool concentration, recurring normalized queries, and top failure reasons. That is far more specific than a tautology. It stops short of naming a sibling, so the agent must infer on its own that impala_query_details or impala_query_ranking are different views.

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?

Usage is implied rather than stated: the tool is framed as an overview within a window, which suggests use for triage or health checks. There is no explicit guidance on when to pick this or when to pick impala_query_details or impala_query_ranking, and no stated prerequisites.

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