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

With no annotations, the description carries the transparency burden. It reveals a distinct ranking methodology ('ranked by Cost/IQ'), output specifics ('plain-English why', 'hot-swap endpoint_config', 'as-of timestamps', 'runner-ups'), and filter semantics (e.g., reasoning filter, modality default). It falls short of full transparency by not describing limits/pagination, error behavior, or edge cases like no-matches.

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 description is compact, front-loads the core answer role, and then packs the remaining behavior into a tight list. The phrase 'ranked with receipts' is colorful but not wasteful. It earns its length because it conveys ranking logic and output fields that are not otherwise available.

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?

The tool has 7 optional parameters and no annotations, and this description explains their meaning and covers the output shape ('returns ranked recommendations with endpoint_config and ranking evidence'). It doesn't fully document ranking-definition for Cost/IQ or the exact endpoint_config structure, but the output schema plus this description make the tool sufficiently clear for an agent to invoke and interpret results correctly.

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 compensate. It explains the meaning of budget_max_usd_per_m ('Max blended price $/M'), context_min ('Minimum context window in tokens'), modality enum ('text' default, 'vision', or 'any'), zdr ('Require zero-data-retention providers'), eu_sovereign ('Require EU-sovereign providers'), reasoning ('Filter reasoning models (null = any, true/false)'), and limit ('Max recommendations (1-20, default 5)'). That is nearly full semantic coverage; it could also mention lower-is-better for Cost/IQ in the params, but overall strong.

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 states a specific verb ('Recommend'), a clear resource ('best-value AI models for given constraints'), and a distinctive ranking criterion ('Cost/IQ (quality-adjusted price, lower is better)'). It clearly distinguishes itself from siblings like search_models and explain_model by describing the ranked recommendation output with receipts.

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 description explicitly frames this as 'the core answer endpoint' and says to 'give it constraints' to get ranked recommendations. It indicates option defaults like modality 'text' and reasoning filter null, and describes output elements that imply when to use it versus searching/catalog tools. It doesn't name alternatives explicitly but gives enough usage context.

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