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

Annotations already carry readOnlyHint=true and destructiveHint=false, and the description's closing 'Read-only' is consistent with them. Beyond that, the description discloses three genuinely non-obvious behaviors: the credential-dependent live-vs-note fallback, the privacy-preserving redaction policy (code-derived signatures never expose raw user messages), and the multi-source join with the JS-thread Stability summary.

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 dense sentences, each carrying distinct information: data composition, the stability-summary join, the redaction policy, and the auth-dependent fallback behavior. There is no redundancy and the core purpose is front-loaded; the length is justified by the complexity of the tool's data model rather than padding.

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 carries the return-value burden and largely succeeds: it conveys per-crash structure, ordering (newest first), the joined stability section, and the no-credentials/no-data edge cases. Minor gaps remain — no mention of result limits or pagination, and no explicit sibling routing for raw-trace or sample-level needs — but these are small against the overall richness.

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% — both install_id and read_token have thorough schema descriptions covering their source, the local-stdio env fallback, and the read-only scoping of the token. The tool description adds no parameter-specific detail, but at this coverage level the baseline of 3 applies; no compensation is needed.

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 resource — crash classes recorded on the device — and enumerates its exact contents (error name, redacted top frame, occurrence-count bucket, relatedRules) plus the three crash categories it covers. It distinguishes itself from siblings like boosthis_full_stack_trace by emphasizing that signatures are code-derived, never raw messages.

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 conditional usage context: it answers live when read credentials are configured and falls back to a dashboard-pointing note when they aren't or when no crash has been recorded. It cross-references boosthis_get_rule for interpreting relatedRules, but never explicitly states when to prefer this tool over sibling alternatives such as boosthis_full_stack_trace or boosthis_recent_samples, leaving routing to inference.

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