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

Annotations already declare readOnlyHint=true, and the description correctly stays consistent with a read-only catalog. It adds genuine behavioral context beyond the annotations by stating what each operation returns (all public prompts, all workspace-scoped custom prompts, full prompt text) and by noting that list operations need no additional params. It omits any auth/permission prerequisites for workspace-scoped reads.

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?

The numbered operation list with paired parameter/return lines is front-loaded and scannable, and the menu-vs-details split is easy to parse. There is minor repetition in the repeated 'Returns:' pattern, but no sentence is wasteful.

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 five-parameter dispatcher with an output schema present, the description supplies everything needed to select the right request value and parameter combination, and it redundantly but helpfully sketches return contents. Nothing an agent needs in order to invoke it 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 description coverage is 0%, so the description carries the full burden, and it does: request enum values, prompt_type='custom', workspace_id for custom scoping, prompt_id for detail lookups, and is_custom=True for the custom-details branch are all given concrete usage contexts. The conditional relationship between parameters (which combos belong to which mode) is exactly the semantics the schema lacks.

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 names a specific resource (Enrichment prompt catalog) and enumerates the four distinct operations it dispatches, each with its request value and return payload. An agent can tell exactly what each call does without opening the schema, and the scope is narrow enough that confusion with query_data/query_contexts/execute_action 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?

It gives explicit parameter recipes for each of the four modes (e.g. request='menu', prompt_type='custom', workspace_id=<int>), which functions as clear when-to-use guidance for each operation. It stops short of stating exclusions or how the tool relates to sibling tools like query_data, so it is not a full 5.

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