Unified Incident Summary

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

Annotation declares readOnlyHint=false, so this tool mutates or writes state, yet the description only speaks of 'collecting' and never discloses what is written or where. The one disclosure it does add—'Reports no_signals when nothing failed'—is useful return-behavior context, but the write side effect is a real gap.

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?

Two sentences with the artifact list and evidence source front-loaded, and the no_signals fallback at the end. No filler, though the enumerated list is dense and would benefit from a short scope qualifier.

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 nested object parameters, no output schema, and only a single annotation, the description should carry more weight. It leaves the shape of the three report parameters and the mutation behavior undefined, which is inadequate for an agent assembling a call.

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 only 25% across four parameters, and three (comparison, chaos_report, evaluation_report) are untyped nested objects with no field documentation. The description gestures at 'supplied evidence' but never maps to those parameters or explains their expected shape, so it does not compensate for the coverage gap.

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?

Names a specific verb ('Collect') and enumerates concrete artifacts collected (regressions, chaos crashes/timeouts, failed evaluation cases, blocked release gates) plus the evidence source. It does not differentiate itself from nearby siblings such as tower.incidents, tower.investigate, or lens.report_summary, so an agent still has to infer which summary tool to pick.

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 phrase 'for investigation' and 'from supplied or session evidence' implies the context of use, but there is no explicit when-to-use vs when-not, and no alternative tool is named. Usage has to be inferred from the sibling list rather than the text.

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