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

Annotations already include readOnlyHint=true, and the description reinforces this with 'Read-only, computed on demand from the execution log'. It adds non-obvious semantics: dropoff is null when no stage is actionable, large stopped counts on the first block are normal, and absence of a flow means unmeasured rather than healthy. This goes well beyond annotations and prevents misinterpretation.

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 longer than typical, but every sentence carries unique information: result contents, dropoff semantics and caveat, entry-flow exclusion, read-only provenance, and a recommendation guardrail. It is front-loaded with the main purpose and tightly edited with no filler.

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?

There is no output schema, so the description compensates by enumerating the measured values (entries, blocks reached, stop rates, dead buttons, goal counts) and defining the dropoff field. It also covers data source, read-only nature, and action guidance. An agent can decide when to call it and interpret the result without needing additional context.

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 100%, and the schema fully documents applicationId: optional, key-scoped default behavior, failure mode MCP_APPLICATION_REQUIRED, and how to obtain the id via list_applications. The tool description adds no parameter-specific information beyond the schema, so the baseline of 3 is appropriate.

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?

States a specific verb ('Return'), resource ('measured conversion funnels of the workspace's ENTRY flows'), and time window ('last 30 days'). It also defines what counts as an entry flow and explicitly excludes menu-button, sequence, and operator-handoff flows, which differentiates it from related flow-analytics tools. Scope is unambiguous.

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?

Clearly scopes when to call it: only for entry flows that a person can start themselves, and it explicitly says flows reached from menu buttons, sequences, or operator handoffs are not measured here. It also gives a decision rule: propose nothing when funnels are healthy or too thin. It does not name an alternative tool explicitly, so the 'vs alternatives' guidance is strong but slightly implicit.

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