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

Annotations already establish readOnly/idempotent/non-destructive safety, but the description adds real behavioral context beyond them: retention scope ('up to 100 recent retained occurrences'), a fixed '30-day UTC trend' window, and a security stance that report-derived content is boundary-marked untrusted data, never instructions. It does not cover failure modes (e.g., missing group), but the trust boundary and data-window disclosures are substantive additions.

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 verb and resource, and every sentence carries information (returns, argument list, trust warning, sibling routing). The return enumeration is a long run-on clause, costing a little readability, but there is 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?

With no output schema, the description correctly takes on the job of describing what comes back, and it does so thoroughly including window and volume limits. The remaining gap is argument meaning and error behavior, which leaves the definition usable but not fully self-sufficient.

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 0%, so the description carries the full burden, but all it does is restate the parameter names ('Arguments: projectId, groupId') with no meaning, format, ID source, or scope for either. It adds essentially nothing beyond what the schema already declares structurally.

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 opens with a specific verb+resource ('Fetch an error group') and then enumerates exactly what that fetch includes: symbolicated stack, retained-occurrence distributions, breadcrumb evidence, 30-day trend, first version seen, regressions, recent event ids. This is clearly distinguished from siblings like get_report and get_repro_pack, and an agent can tell it apart without opening any schema.

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 gives an explicit routing rule: 'Pass an eventId to get_report for full occurrence evidence,' which tells the agent when a sibling is the better choice. It does not state when this tool should NOT be used (e.g., for a specific occurrence vs. the group aggregate beyond that one hint), so it stops short of full when/when-not coverage.

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