query_retention_analysis

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the read-only safety is covered. The description adds the temporal relationship between initial and returning events, which is useful behavioral context. However, it doesn't disclose output format, time range semantics, or any other behaviors, so it doesn't go beyond the annotations meaningfully.

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?

A single, front-loaded sentence with no redundant words. It communicates the core action and key entities efficiently. The brevity is not padding but under-specification, yet for this dimension it deserves full marks for conciseness.

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?

Given the complexity (nested objects, output schema, sibling analytical tools), the description is minimal. It lacks context on what retention metrics are returned, how cohorts are defined, or how time_range options behave. The presence of an output schema reduces the need to explain return values, but the core semantic of retention analysis is not fleshed out, making the tool hard to use correctly for an agent.

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 must compensate. It clarifies the role of initial_event and returning_event (as start and end events) but provides no explanation of time_range (start_time/end_time vs recent_day). The nested object structure is also unexplained, leaving a significant portion of the parameters semantically ambiguous.

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 uses a specific verb ('Query') and resource ('retention') with the initial/returning event relationship. It clearly states what the tool does and distinguishes from siblings by focusing on retention, though it doesn't explicitly contrast with funnel or path analysis.

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 no guidance on when to use this tool over siblings like query_funnel_analysis or query_event_analysis, nor any exclusions. It only implies usage through the term 'retention', which is insufficient for an agent to select among the many analytical siblings.

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