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

Annotations already declare readOnlyHint=true, so the safe-read aspect is covered. The description adds real behavioral context beyond that: the return payload is a paged Feed with Size, Items, Previous and Next, which tells the agent to expect pagination cursors rather than a flat array. No rate-limit or auth behavior is mentioned, keeping it short of a 5.

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?

Front-loaded with purpose and return shape, then endpoint, then filtering/ordering, then the alternative. Dense but every sentence carries information; the brace-notation Feed summary is slightly compressed for readability but not wasteful.

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 supplies the return shape (paged Feed) and covers filtering, sorting, pagination and the operator escape hatch. For a 5-param nested-object tool it is nearly complete, lacking only error/empty-result behavior and any note on default paging semantics beyond what the schema says.

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%: page, params, sortby, pagesize and takesize are all documented in the schema, including the same equals-style example and the same textemall_request escape-hatch hint. The description therefore largely restates the schema, which sets the baseline at 3, though the inline operator example (StartDate~gte~2024-01-01) makes the constraint more actionable.

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?

Specific verb + resource ('List broadcasts') with an explicit scope note that it covers both text and voice campaigns, plus the underlying endpoint GET /v1/broadcasts. It distinguishes itself from the sibling get_broadcast (singular) and textemall_request (named as the escape hatch for operators this tool can't express).

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 states how to filter (equals-style `params`) and how to order (`sortby`), and explicitly routes a specific case — date-range operators like StartDate~gte~2024-01-01 — to the textemall_request sibling. There is no broader when-not guidance (e.g. when to prefer get_broadcast or list_lists instead), but the condition-based routing is concrete.

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