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

readOnlyHint=true already tells the agent this is a safe read, so the description's added burden is lower. It does disclose that 'menu' returns only public/system prompts and that workspace-scoped bodies require is_custom plus workspace_id, which is useful context, but says nothing about pagination, result size, or failure behavior.

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?

Three short blocks, front-loaded with the catalog purpose, then a tight enumeration of modes with their required params. No filler sentences.

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 need not be described, and the mode-per-parameter mapping is complete enough to call the tool correctly. The remaining gap is the allowed value set for prompt_type and whether the menu is paginated.

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 load, and it does define the role of every parameter: request's two modes, prompt_id for body fetch, prompt_type and workspace_id as menu filters, and is_custom as the workspace switch. It stops short of giving types or valid prompt_type values.

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 and resource ('Browse the OpenAI Ads prompt catalog') and then enumerates the two operations the tool multiplexes. It is clearly not a data-query or action-execution tool like its siblings, though it doesn't name those siblings explicitly.

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?

The numbered list maps each request value to a concrete intent and states the conditional prerequisite for workspace prompts ('Set is_custom=True + workspace_id'). It gives clear positive guidance but no exclusions or routing advice relative to query_data / execute_action.

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