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

readOnlyHint=true already declares the safety profile, so the bar is lower, and the description adds real behavioral detail beyond it: result ordering (newest classification first), paging semantics ('total is the count before paging, so the whole tail is reachable'), untagged taking precedence over tag_id, and the senders edge case where an unknown email is dropped and an empty remainder yields an empty result. Auth/rate-limit context is absent but not expected for a 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?

Front-loaded with a one-sentence summary of the tool's role before the filter and paging guidance, which is the right order. It is dense and somewhat long, and several filter explanations duplicate the schema, but almost every sentence carries information an agent needs.

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 carries the full return-value burden and does so thoroughly: it documents the returned dict shape (group_id, total, people[]), the nested person identity used by the shared person-card modal, and that outcome is OR-ed across in-scope prospects. For a nine-parameter read tool this is complete enough to call 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?

Schema description coverage is 100%, so every one of the nine parameters is already documented in the schema, including the same tag_id/untagged/senders/agent_ids semantics the description restates. The description adds essentially no syntax or format detail beyond the schema, so the baseline of 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?

States a specific verb+resource ('the per-person drill-down for a segment group') and enumerates exactly what each row contains: classified people newest-first, their tags, the canonical person identity, and OR-ed outcome flags. The framing as a 'drill-down' implicitly positions it against the aggregate segment tools (get_segment_funnel, get_segment_rates, get_segment_unclassified_count), so an agent can distinguish it without opening a 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?

Gives clear operational context via the filter semantics — tag_id for tagged people, untagged=true for 'No match' people, agent_ids to scope by campaign, senders to scope by teammate — and notes paging behavior. It does not, however, explicitly say when to choose this over query_people/query_agent_people or the aggregate segment tools, so there is context but no stated alternatives or exclusions.

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