Facet a query across dimensions (ranked top-N counts)

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

Annotations declare readOnlyHint=true (safe read) and the description reinforces this with 'every job auto-deleted.' It discloses concurrency, error handling (one failing dimension never total failure), and the behavior of dimensions (native vs. parsed). No contradictions with annotations.

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 description is dense with information, front-loaded with purpose and key traits. Every sentence contributes, but slightly verbose (e.g., 'exactly ONE of'). Could be trimmed slightly without losing meaning.

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?

The description comprehensively covers behavior given no output schema and 8 parameters. It explains error handling, concurrency, dimension naming conventions, and time range constraints. The agent can confidently invoke this tool based on the description alone.

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 covers all parameters descriptively (100% coverage), but the description adds valuable semantics: explains '_' prefix for native fields, JSON payload parsing for others, and clarifies time range mutual exclusivity. This adds meaning beyond the schema alone.

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 clearly states the tool's purpose: 'fastest way to see the SHAPE of matching logs before reading any messages.' It specifies the action (facet across dimensions, count by dimension) and distinguishes from siblings like sumo_run_search by emphasizing aggregate results. The resource and verb are specific.

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 implies usage for initial exploration ('before reading any messages'), and explains time range options and error handling (one failing dimension yields error line, not total failure). However, it does not explicitly contrast with sibling tools like sumo_trend or sumo_run_search, leaving some ambiguity about ideal use cases.

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