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

The annotations already declare readOnlyHint=true and openWorldHint=true, but the description adds substantial behavioral context: the call is free, returns only ids/dates/counts, does not return row content, and row content is sold separately through x402. This is exactly the kind of cost and output-scope disclosure an agent needs beyond the annotations.

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 front-loaded with the endpoint and free status, then the return shape, pagination, and the paid-content limitation. Every sentence adds relevant information with no padding.

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 two-parameter read-only index tool with no output schema, the description covers the return fields, the absence of row content, pagination, and the paid-content boundary. An agent has enough information to call it correctly and understand what it will and will not receive.

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%, and the schema already explains that limit is rows per page (1-500) and start is the first row id. The description adds only that these parameters page through row ids, which is useful but not meaningfully beyond 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 gives a specific endpoint, scope, and return contents: GET /v1/index, free row ids and UTC dates without row content, row count, first/last dates, and dates with rows. It also explicitly distinguishes this from paid row-content retrieval, so an agent can identify it as a metadata-index tool rather than a content or pricing tool.

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?

It clearly states that start and limit are used to page through row ids and that row content is not returned here, which gives useful context for when this tool fits. However, it does not name sibling tools like receipts_sample or receipts_pricing or explicitly route the agent to them for row content or pricing.

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