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

Annotations only declare readOnlyHint, so the description's addition of the public/system vs. workspace prompt scope and the prerequisite parameters for workspace prompts is genuinely useful context. It says nothing about pagination, result size, or error behavior, which keeps it from a 5.

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 lines: a one-sentence purpose followed by a numbered mode list. The catalog scope is front-loaded and every sentence adds a distinct routing fact.

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 5-parameter, 0%-coverage router with an output schema handling return values, the description covers mode selection and conditional parameter requirements. The only minor omission is valid prompt_type values, which is secondary to correct invocation.

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?

With 0% schema description coverage, the description carries the burden and mostly succeeds: both enum values for request, prompt_id, is_custom, and workspace_id are explained. The gap is prompt_type, which is only said to be 'optionally' passable with no hint of valid values or effect.

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 opening line names a concrete resource ('TikTok Profile prompt catalog') and the two numbered modes give specific verbs (list prompts, fetch prompt body). An agent can tell exactly what the tool does; the unrelated siblings (execute_action, query_data) don't require explicit differentiation.

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?

Each request value is paired with its purpose, and the guidance 'Set is_custom=True + workspace_id for workspace prompts' tells the agent which additional parameters a given path requires. There is no explicit when-not-to-use or alternative-tool routing, but the mode split provides clear selection context.

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