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 useful traits: it is read-only, it is free (no credit cost), and the payload can be large. It omits practical concerns such as any row/size ceiling, whether huge audiences time out or truncate, and whether the call counts against rate limits.

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?

One sentence plus two short fragments, front-loaded with the action and immediately followed by the return shape. Every clause earns its place: return fields, size warning, safety and cost.

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?

No output schema exists, and the description compensates by enumerating the return keys, which is exactly what an agent needs to plan parsing. For a one-parameter export tool the remaining gap is only the absence of any size or failure-mode limits.

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?

There is a single parameter and schema coverage is 100%, so the schema already documents 'id' as a custom audience UUID. The description adds only the audience scoping context and nothing about format or lookup failure behavior; baseline 3 applies when the schema does the heavy lifting.

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 and resource: downloading every contact of a custom audience as CSV text, plus the exact return fields (filename, total_rows, csv). An agent can distinguish it from get_custom_audience_contacts or sdr_export_people_csv, though the description never names those siblings explicitly.

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: 'every contact' plus 'Can be large' signals this is a bulk-export path rather than a paginated listing. No explicit when-to-use statement, no mention of alternatives like get_custom_audience_contacts, and no prerequisite conditions.

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