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

With no annotations, the description does real work: it discloses the zero-credit cost, and that smart segments are evaluated at call time against the people table rather than read from storage — a meaningful behavioral distinction. It does not state truncation behavior when limit (max 5000) is hit, whether results are ordered, or what happens for an unknown/invalid segment_id.

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?

Three short sentences, each earning its place: definition and return type first, per-type behavior second, cost last. Zero padding and no restatement of the tool name.

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?

For a 2-parameter read tool with a 100%-covered schema and no output schema, the description covers what is returned (person_ids), how it is produced per segment type, and its cost profile. The remaining gap is pagination/truncation semantics against the 5000 max limit, which the agent would need for large segments.

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 segment_id and limit (default 1000, max 5000) are already fully documented. The description mentions the `config` predicate that segment_id ultimately resolves, but adds nothing about how limit bounds or truncates the returned list. Baseline 3 applies when the schema carries full parameter load.

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 and the exact output shape: 'Resolve an audience segment into a concrete list of person_ids.' It even breaks the purpose down by segment type (manual/auto_stream vs smart), which is unusually informative. It never names the closest sibling, resolve_collection, so sibling differentiation is implied by resource name only.

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 explains the two operational modes ('returns stored members' vs 'evaluates the segment's config predicate against the people table'), which tells the agent when results are cheap/likely-instant versus computed. The 'Free — costs 0 credits' line gives a concrete reason to prefer this over credit-consuming siblings. There is no explicit when-not-to-use or named alternative, though.

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