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

readOnlyHint=true is consistent with the description, which describes only retrieval of metadata, action definitions, and guidelines — 'write actions' refers to actions being planned, not performed here. Beyond annotations, it discloses what each response contains (workspace_id, brand_id, ad_account_id, available_actions, exact request body, required identifiers, fields, time ranges, notes) and flags that the standalone `available_actions` call is redundant with the accounts response.

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-loaded workflow, and each mode labeled with its purpose and payload. The optional `available_actions` line spends a parenthetical noting redundancy, which is useful but slightly padded; otherwise there is no wasted text.

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 multi-mode tool with five parameters, the description establishes the full call sequence and output expectations, and an output schema exists so return-value detail need not be restated. The one real hole is `platform`, which is neither described nor contextualized, so an agent cannot confidently decide when to supply it.

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 burden — and it explains four of the five parameters well: all four `request` enum values, the `actions` array with its source (available_actions) and its requirement for `actions_details`, and `brand_id` + `workspace_id` for the brands mode. `platform` is never mentioned, leaving one parameter with no semantics anywhere.

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 discovery/planning helper for InsightfulPipe OpenAI Ads that returns account metadata, action details, and brand guidelines. The enumerated `request` modes make the scope concrete. It does not name the siblings (execute_action, query_data) directly, so differentiation relies on the strong implication that this is the preparatory metadata step rather than the query or execution step.

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 ordered workflow: Step 1 `accounts`, Step 2 `actions_details` and marked 'REQUIRED before querying', then optional modes with their conditions. This tells the agent exactly when to call what and in what order. What it lacks is any exclusion — it never says when to skip this tool and go straight to query_data or execute_action.

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