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

The description reveals that the call may not return a record for every domain and explicitly instructs comparing requested vs enriched counts. It also communicates a scale limit ('up to 10'). These behaviors go beyond the readOnly/idempotent annotations, giving the agent essential expectations about partial successes.

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?

Four sentences each cover a distinct necessity: the core action, the input, the output/caveat, and the single-domain alternative. No fluff; the most important info is front-loaded.

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 bulk read-only tool with an output schema, the description covers purpose, payload, count-obsessed output semantics, and sibling routing. It gives an agent everything needed to select and call the tool 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?

The schema already documents `domains` as an array of bare domains with format guidance, so the description adds little on domain format. However, 'Enrich up to 10 companies' adds a max array-size hint not present in the schema, raising it above baseline.

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?

The description states a concrete action ('Enrich up to 10 companies in one call'), ties it to the `domains` array, and explicitly contrasts with `get_apollo_organizations_enrich` for a single domain. This clearly distinguishes the bulk POST from its sibling GET.

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 specifies the bulk use case ('up to 10 companies in one call') and directs single-domain needs to `get_apollo_organizations_enrich`. It also warns that not all input domains will resolve, which affects how the agent evaluates results.

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