cf_ai_models

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

With no annotations, the description carries the full burden, and it discloses that results are model metadata plus capabilities (a read-only listing), which is useful. It does not mention pagination, result limits, or auth requirements, and its brevity limits how much behavioral context an agent gains.

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?

Two compact sentences, with the primary action front-loaded before the examples. The parenthetical is somewhat dense but every element adds discriminating information, so there is little waste.

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?

An output schema exists, so return values need not be described, and the description correctly covers purpose and output nature. However, with zero annotation coverage and an undocumented search parameter, it leaves gaps around search semantics and result set behavior.

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% for the single 'search' parameter, so the description must compensate. The verb 'search' plus concrete example tokens ('@cf/meta/llama-3', 'embeddings', 'text generation', 'vision') convey what can be matched, giving more meaning than the bare default-empty string schema.

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 ('List or search Cloudflare Workers AI models') and the parenthetical enumerates model categories (llama-3, embeddings, text generation, vision), making the tool's scope unambiguous. No sibling tool covers AI models, so differentiation is inherent.

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?

'List or search' implies the two modes (browse vs. filter via the search parameter), but the description never states when to prefer one, nor any prerequisites or alternatives. Usage is implied rather than spelled out.

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