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

With no annotations, the description still discloses the two behaviors an agent would most worry about for a write tool: it sends nothing ('no outreach happens here') and costs nothing ('no credits'). It also names the return value. It does not say whether re-saving the same filters creates a duplicate audience or how persistence/naming collisions are handled.

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 sentences, front-loaded with purpose, then prerequisite, then output destination and cost disclaimer. No filler, no restatement of the title.

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 filter-heavy creation tool with no output schema and no annotations, it covers the workflow, the non-side-effects, and the return value. The remaining gap is filter field semantics, which it mitigates by pointing at search_audience rather than enumerating fields.

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?

At 50% schema coverage and a deeply nested filters object of ~27 fields, most properties (city, tags, industries, searchMode, companySize, mustHave*) have no per-field docs. The description does compensate usefully by tying the filter shape to search_audience, implicitly deferring semantics to that tool, but it adds no field-level meaning itself; the auto-naming behavior of `name` lives only in the schema.

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 ('Save a campaign audience') plus where the input comes from ('the same filter set as search_audience'). This cleanly separates it from search_audience (preview counts) and create_campaign (consumer of the returned id).

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 an explicit prerequisite ('call that first to check the counts') and an explicit downstream step ('Returns the audience id to pass to create_campaign'). Also excludes a wrong expectation ('No outreach happens here'), so the agent knows this is not a launch step.

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