Get metric trend (crash + drop rate)

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

No annotations are provided, so the description carries the full disclosure burden. It explicitly defines both rates, states that rates are null for an empty window and deltas null without a baseline, and reveals the returned object shape. This gives the agent clear behavioral expectations before invoking.

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 definition is compact and front-loaded: the opening question states purpose, followed by formulas, edge cases, and output shape. Every clause contributes, and there is no filler or redundant schema repetition.

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 compensates by giving the exact return fields and null semantics. It also addresses empty-window and missing-baseline cases, and the schema covers the parameters. A caller has enough information to invoke the tool correctly.

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?

All three parameters have schema descriptions, so the schema already covers formats and constraints. The description adds operational context for 'days' as a comparison window, but it does not introduce new parameter formats, defaults, or constraints, so it stays at the high-coverage baseline.

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 identifies a specific computation: crash rate and drop rate for the last N days vs the prior equal window, with percentage-point deltas. It includes concrete rate formulas and names the return object, so an agent knows exactly what the tool produces and can distinguish it from list/funnel/retention siblings.

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 supplies target questions ('is my game crashing more this week?' / 'are more players dropping out?') that tell an agent when the tool is appropriate. It does not name sibling tools or exclusions, but the use-case context is unambiguous and actionable.

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