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

With no annotations, the description carries the full burden and does disclose the safety profile explicitly ('Read-only, free') plus the returned dimensions: status with its enum values (processing|ready|enriching|error), contact counts, enrichment progress. It stops short of stating pagination/truncation behavior or ordering, which matters for a list endpoint that can return everything.

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 dense sentences: the resource definition and its subtypes come first, then the returned fields, then the sibling differentiation, then the read-only/free note. No filler, and the most decision-relevant clause (which sibling) is not buried.

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 usefully substitutes by naming the fields returned and the status vocabulary. The remaining gap is pagination semantics for a zero-required-parameter list call — an agent doesn't know what happens with `page` alone or whether an unpaginated result is safe to consume.

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 only 50% — `limit` is documented in the schema ('Omit to get all') but `page` is undocumented everywhere. The description supplies no parameter guidance at all: no default page size, no note that omitting `limit` returns all records (a cost/volume concern for a 'free' call), and no interaction between `page` and `limit`.

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 (list) and a precisely scoped resource (the workspace's custom audiences), then enumerates what counts as one: uploaded CSV/XLSX lists, purchased audience sets, CRM selections. It explicitly distinguishes itself from campaign audiences via `list_audiences`, so the agent can separate it from that sibling 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 a clear routing rule against `list_audiences` and notes the operation is read-only and free, which is a genuine use-case cue. It does not address the other nearby alternatives an agent might pick instead (`get_custom_audience`, `search_audience`, `list_audience_sets`) or say when a single-record fetch is preferable to listing.

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