get_crash_rate

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

The description discloses return values (daily crashRate, userPerceivedCrashRate, distinctUsers) and a behavioral threshold, but with no annotations, it fails to state read-only nature or safety implications.

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?

The description is concise at 4-5 lines, well-structured with a main purpose line, return info, a threshold note, and parameter descriptions. No wasted words.

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?

The description covers purpose, parameters, and return values adequately for a read operation. It lacks error handling or usage comparisons but is complete for most scenarios. The absence of output schema is compensated by the description.

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?

Despite 0% schema description coverage, the description thoroughly explains all three parameters: package_name (example), days (default and max), and version_code (optional). This adds significant value beyond the schema titles and defaults.

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 'Fetch user-perceived crash rate from Android Vitals,' specifying the verb (fetch) and the resource (crash rate). It uniquely identifies the tool among siblings like get_anr_rate and get_vitals_summary.

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 description provides context with a bad behavior threshold but lacks explicit guidance on when to use this tool over siblings like get_anr_rate or get_vitals_summary. No alternative tools are mentioned.

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