Deduplicated error/warning digest for a scope

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

Discloses key behaviors beyond annotations: normalization (stripping timestamps/UUIDs/hex/numbers), level filter uses log.levelname (reliable), maxScan behavior when truncated, and that level filter is automatically appended. Aligns with readOnlyHint=true.

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?

Every sentence adds value, though the description is somewhat long. It is front-loaded with 'One-call triage' and structured logically. Minor redundancy exists (time range rules stated twice).

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?

Given 9 parameters and no output schema, the description explains return fields and critical parameter behaviors. It lacks information on error handling or rate limits, but is largely complete for its purpose. The annotations and schema descriptions already cover some aspects.

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 100%, but the description adds significant value: the 'query' parameter includes a vital warning about avoiding hostname keywords; time parameters clarify format and mutual exclusivity; levels indicate defaults; maxScan explains truncation. This goes well beyond the baseline.

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: one-call triage that finds ERROR/WARNING messages, groups by normalized signature, and returns top-N problems with count, occurrence times, sample request_id, and sourcecategory. It distinguishes from siblings like sumo_get_messages which would return raw logs.

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?

Provides explicit when-to-use (one-call triage), how to specify time range (exactly one of `last` or both `from`/`to`), and critical caveats like scoping by _sourcecategory not hostname, and not adding | operators since level filter is appended automatically.

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