Funnel

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

Read-only behavior is already declared by readOnlyHint, so the description wisely spends its words on semantics instead: it clarifies that a rejection counts as a reply and that stages come from the tracker configuration, which an agent could not infer otherwise. It does not mention pagination or performance characteristics, but that is a minor omission for an aggregate read tool.

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?

Two sentences, no filler: the first names the metric and its edge case, the second states the aggregation and rate basis. Front-loaded and every clause carries information.

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 an output schema present, full parameter documentation and read-only annotations, the description need only supply the conceptual model, and it does: what counts as a reply and where stage definitions come from. The only gap is the absence of explicit routing guidance among the many sibling analysis tools.

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%, with 'by', 'since' and 'until' each fully documented including defaults and allowed values. The description only alludes to grouping ('per group') and date scoping ('submitted') without adding anything the schema lacks, so baseline 3 applies.

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 states a specific computation: conversion of submitted applications into reply counts and configured funnel stages, aggregated in total and per group with percentage rates. It is clear what the tool produces, but it does not explicitly distinguish itself from analytics-focused siblings such as summary or reply_times.

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?

Usage is only implied by the tool's analytical nature; there is no explicit statement of when to use this versus summary or reply_times, nor any exclusions or prerequisites. The 'as configured' phrasing hints that the tracker must be inspected first (describe_tracker) but does not say so as a precondition.

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