aeo_cluster_prompts

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

Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description does add real value beyond that: prompts are sent to OpenAI for embeddings, which is a data-egress disclosure an agent should surface to a user, plus hard size limits. However it is silent on cost, latency, or what happens when limits are exceeded.

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?

Tight and front-loaded: purpose first, then input contract, then return shape, then the external-provider note. The trailing '[Provider: OpenAI]' line restates the embedding-provider sentence just above it, a small redundancy.

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 no output schema, the description compensates by describing the return value ({clusters with members, n_items, n_clusters}), which is genuinely needed. It is nearly complete for a 3-parameter tool; only the semantics of `brand` and `distance_threshold` are 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 must carry parameter meaning. It documents the `items` element shape ({id, text, intent?, volume?}) and the 140-item / 300-character limits well, but never explains `brand` or what `distance_threshold` (default 0.35) controls, leaving two of three parameters undefined in both schema and description.

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 with the underlying method: 'Group prompts into topic clusters by text embedding similarity.' The method phrase implicitly separates it from the URL-based clustering sibling, though no sibling is named 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?

Operational constraints are given (max 140 items per call, each text up to 300 characters), which tells an agent when the tool will fail, but there is no explicit guidance on when to choose this over aeo_cluster_by_urls or the other aeo_ prompt tools, nor any stated prerequisites.

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