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

Annotations already declare readOnlyHint=true and idempotentHint=true, covering safety. The description adds behavioral context by enumerating the event types and stating the ordering and pagination behavior. It does not describe the return structure or error handling, but the annotations reduce the burden, so this is sufficient.

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 three short sentences, front-loading the core purpose and then adding filtering and pagination. Every sentence earns its place with no fluff. It is concise and well-structured.

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 description covers the essential aspects: event types, ordering, filtering, and pagination. It does not describe the structure of the returned events, but no output schema exists, so some ambiguity remains. Given the tool's simplicity and annotations, this is reasonably complete, though it could mention what fields an event contains.

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 coverage is 60%, with descriptions for model, cursor, and provider. The description adds meaning to 'kind' by listing the event types that correspond to the enum, and confirms filtering for provider and model. However, it doesn't add much beyond the schema for limit, which is standard. Overall it provides marginal value over the 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?

The description clearly states it lists catalog events with specific types (added, removed, returned, price changes, free/paid, new gateways) and orders them newest first. This distinguishes it from sibling tools like compare_model_prices or search_models, which serve different purposes. The verb 'list' and resource 'catalog events' are specific.

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 provides operational guidance on filtering by gateway or model and paginating with a cursor, but does not explicitly state when to choose this tool over siblings. The purpose implies it for browsing recent changes, but no exclusions or alternative conditions are given. This is adequate but not explicit.

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