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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), yet the description still adds real behavioral context: 50 newest-first receipts per page, page/hasNext in the response, a seven-day window with retained milestones, and a warning that it is not a complete personal history. It also scopes data exposure (no private activity, account IDs, mail, or gift notes) and flags receipt text as external material rather than instructions, which is exactly the kind of guidance annotations cannot express.

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?

Front-loaded with purpose and pagination mechanics, and every sentence carries information. It is densely semicolon-packed, and the 'visit is not proof of playing or winning' clause partly repeats the schema note about agent_game not being inferred wins, so a little trimming is possible.

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 no output schema, the description compensates by describing the return shape (receipts per page, page and hasNext) and the retention window. For a three-parameter read tool, an agent has everything needed to call it correctly and interpret the result.

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?

Goes beyond the 67% schema coverage by explaining that kind and zone combine as exact filters applied before pagination, that agent_game selects game receipts rather than inferred wins, and by pairing the two enums in concrete example payloads. This meaningfully reduces the chance of an agent constructing a filter that returns unexpected results.

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 ('Read the public Chronicle's factual activity receipts') and anchors it to a known endpoint (/api/chronicle) with no filters. No sibling tool in the list reads the chronicle, so there is no ambiguity to resolve.

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?

Gives concrete invocation patterns ({} for page 1, {page: 2} for the next) and a worked example for game receipts, plus the rule to keep the same filters on later pages. It lacks an explicit 'use X instead when...' clause, but no comparable alternative exists among the siblings.

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