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

Annotations already declare readOnlyHint=false, destructiveHint=true, openWorldHint=true, so the safety profile is partly pre-supplied; the description nonetheless adds real value by warning about irreversibility, requiring intent confirmation, and documenting platform-specific write restrictions (Pinterest Ads/Pages create-update only, delivery stays PAUSED). It does not describe what a successful or failed execution returns or how partial failures behave across platforms, which is the main behavioral gap. Scored 3 rather than 5 because much of the safety framing overlaps what destructiveHint already conveys.

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 the purpose, then prerequisites, then the destructive warning, then platform rules — a sensible priority order for a write tool. It runs long and the 'Use for creating posts, updating products...' list partially restates the opening parenthetical, but every remaining block carries actionable information.

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 destructive, open-world tool with an opaque two-parameter schema, the description covers the prerequisite workflow, the irreversibility warning, and per-platform write limits; the output schema (present) handles return values. Nothing an agent needs in order to call this correctly is missing.

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 0% and `body` is an untyped open object, which would normally be a serious gap. The description compensates by mandating a discovery step (actions_details) to obtain the exact body structure before calling, which is the most useful thing it could say given a free-form body. It still gives no inline hint about what `platform` accepts (no enum, no examples of valid platform strings).

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 class (write operations) plus the concrete action families it covers (create, update, delete, publish, send) and ties them to the InsightfulPipe raw actions API. It explicitly separates itself from the sibling query_data by naming read-only queries as out of scope, so an agent can route without opening either 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 explicit when-to-use examples, an explicit when-not (read-only → query_data), and names the companion tool query_contexts. The three-step prerequisite sequence (accounts → available_actions → actions_details) with exact request/parameter values is actionable routing guidance, not just context.

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