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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds genuinely non-obvious behavior: the accounts response bundles available_requests, and actions_details is a mandatory prerequisite that yields exact request bodies and identifiers. It stops short of describing response shape or failure modes, but the ordering constraint is the important disclosure.

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?

Numbered steps front-load the primary flow and the final sentence cleanly marks the optional paths. Minor waste: the parenthetical about available_actions being already included is repeated information, and 'Helper for planning' is thinner than the steps that follow.

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 an output schema present, return values needn't be explained, yet the description still summarizes what each response contains — a net gain. For a five-parameter dispatch tool the workflow is complete enough to call correctly, with the unmentioned 'platform' parameter the only real omission.

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 0%, so the description carries the full burden. It documents all four request enum values with intent, plus actions, brand_id, workspace_id — but the 'platform' parameter is never mentioned anywhere. That leaves one of five parameters entirely undocumented, which caps this below a 4 despite strong enum coverage.

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 specific role: a setup/planning helper that returns account metadata and per-action request specs, rather than returning ad data itself. That separates it in spirit from query_data and execute_action, though those siblings are never named. An agent knows what it fetches but must infer the boundary from the step ordering.

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?

Explicit sequencing is given: call request='accounts' first, then request='actions_details', which is marked REQUIRED before querying. It also flags that 'available_actions' is redundant with the accounts response, which is a real usage decision. What's missing is naming the downstream sibling (query_data/execute_action) that this gates.

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