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

With annotations only declaring readOnlyHint, the description carries real behavioral weight: each person is counted once (so rates differ from per-channel tools), funnel.reached counts everyone who got at least that far while other stage keys count only people currently at that stage, auto-tagging of new people within ~15 minutes, plus the not_tagged/out_of_credits/'No match' semantics and the thin/early/solid signal thresholds.

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?

It is long but front-loaded: the summary sentence comes first, followed by the divergence warning, then quoting guidance, then returns. Every block earns its place against the toolbar's complex nested output, though the embedded returns section is denser than it needs to be.

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, and the description compensates fully: it enumerates the return keys (groups, selected, credits_per_person), the funnel shape, the per-tag entries carried by everyone, signal thresholds, and the null-tag fallback entry. Nothing an agent needs to interpret or call the tool is missing.

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%, so both parameters are already documented, including the omit-for-first-covering-group default. The description corroborates this ('Omit for the first group that tags this campaign') and ties group_id to the `groups` output, but adds no new syntax or format meaning beyond the schema, which is the baseline-3 case.

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 summary states a specific verb+resource: one campaign's lead funnel split by a segment group's tags, mirroring the campaign Summary view filtered by tag. It explicitly names and distinguishes itself from get_segment_rates ('which scores each channel separately'), so an agent can tell the two apart without opening either schema.

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?

It gives concrete motivating questions ('how are VPs doing on this campaign', 'which seniority replies best here'), states the alternative and when it applies (get_segment_rates when channel-level scoring is needed), and routes the drilling-down case to query_task_people with the exact filter set to use.

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