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

Annotations already cover readOnly/openWorld/idempotent, so the bar is lower; the description still adds valuable context by disclosing the costly-call mechanism ($0.003 in USDC per call, x402 or prepaid credits) and that it is a live-data (non-cached) catalog. It does not mention rate limits or result-size behavior.

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?

Effectively two content-bearing sentences that front-load the catalog scope and returned fields before the payment terms. Dense but every clause earns its place; the 'Filter by Price: $0.003' phrasing is slightly garbled but brief.

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 an output schema present, annotations, and 8 fully-documented params, the description only needs to establish scope, coverage breadth, returned fields, and the payment gate — all of which it does. The remaining gap is sibling routing against ai-models-pick.

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 100%, so params are fully documented structurally; the description only restates the filter concepts (price, provider, features, context length) without adding syntax, defaults, or interaction rules. Baseline 3 applies.

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 resource (live prices and specs of 400+ AI models) and enumerates exactly what is returned: input/output token prices, cached-input price, context length, max output, and capability flags. It does not name or differentiate itself from the sibling ai-models-pick, which is the one thing an agent needs to disambiguate.

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?

Usage is implied by the filter/field enumeration (browse and compare models by price, provider, features), and the payment line conveys the access model. But it never states when to choose this over ai-models-pick or chat/embeddings siblings, nor any when-not conditions.

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