Top error messages

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

Annotations already cover read-only, idempotent, non-destructive, open-world. Beyond that, the description discloses the return shape (counts, affected users, triage status, first/last seen, TrackJS link), the default sort order, and the endpoint. Missing pagination/result-set size behavior, though the schema hints at paging.

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?

Four sentences, front-loaded with what the tool returns, then default ordering, then the primary use case. Slight redundancy in restating sortBy guidance that the schema already carries, but no filler.

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 enumerating returned fields. With fully documented parameters and rich annotations, the only meaningful gap is pagination/result-volume behavior.

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 100%, so parameters are already fully documented, and the description adds only the default sort and the usercount alternative, which largely duplicates the sortBy schema description. Baseline 3 is appropriate.

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 operation: error counts grouped by error message, with a named list of returned fields and the underlying endpoint (GET /errors/messages). This clearly distinguishes it from sibling tools like list_errors (raw error list) and errors_by_url/day/hour (different grouping dimensions).

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?

Explicitly positions the tool as "best starting point for 'what are our most common / most impactful errors?'" and gives a concrete alternative sorting strategy (sort by usercount). It doesn't name sibling tools or state when not to use it, so it falls short of a 5.

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