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

readOnlyHint=true already tells the agent this is a safe read. The description adds that 'menu' returns public/system prompts versus workspace-scoped ones, which is useful behavioral context, but says nothing about pagination, result limits, or what happens if prompt_id is omitted on the details path.

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?

One header sentence plus a two-item numbered list, front-loaded with the mode switch. No filler; every clause maps to a parameter or a branch.

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-value explanation isn't required, and the description covers the mode branching and optional filters. Remaining gap is the unexplained prompt_type vocabulary on the 'menu' path.

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%, so the description must carry the load, and it mostly does: it maps request enum values, prompt_id, workspace_id, is_custom, and prompt_type to their roles. The gap is prompt_type — its accepted values and filtering effect are never explained.

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?

Opens with a specific verb+resource ('Browse the Pinterest Ads prompt catalog') and enumerates the two operations it supports, so an agent immediately knows this is a read-only catalog browser. It doesn't explicitly contrast itself with siblings (execute_action, query_contexts, query_data), but the resource is distinct enough that confusion is unlikely.

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 two numbered entries act as a routing table: use request='menu' to list, request='prompt_details' to fetch a body, with the extra condition that workspace prompts require is_custom=True plus workspace_id. Clear context for selection, though it gives no when-not or fallback guidance.

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