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

With no annotations provided, the description carries the full burden of disclosing behavior. It mentions the event types and the 'since a timestamp' scoping, but it does not explicitly state that this is a read-only operation, describe pagination or rate limits, or explain behavior when no 'since' is provided. This leaves important operational details undisclosed.

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 concise, with the first sentence front-loading the core functionality and event types, and the second giving usage context. It contains no unnecessary words, though the first sentence is a fragment rather than a complete sentence, slightly reducing structural polish.

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?

For a relatively simple read tool with no output schema, the description covers the purpose and the types of changes, and gives usage context. However, it omits the return format, pagination behavior, and the optionality of the 'since' parameter, which are important for an agent to invoke it correctly. It is adequate but not fully fleshed out.

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?

The input schema already documents all three parameters with descriptions, so the coverage is 100%. The description adds little beyond the schema; it restates the 'since' concept and lists event types that mirror the enum values. It does not clarify how parameters interact (e.g., q and type together), so it provides only marginal added value.

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 identifies the resource as market change events and enumerates the three event types (new contracts, price moves, removed contracts), making the tool's focus specific. It also mentions intended use by the live feed and agent context refreshers, providing useful scope. However, it isn't a full sentence and doesn't explicitly distinguish from closely named siblings like get_changes_delta.

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 gives a clear usage context ('Used by the live feed and agent context refreshers'), implying when to call this tool. However, it lacks explicit guidance on when not to use it or which alternative tools might be preferable, such as get_feed or get_changes_delta.

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