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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds genuinely useful pagination behaviour ('one page per call') and the server-side aggregation escape hatch, but says nothing about page size defaults, what limit caps at, or the cost of all_pages scans.

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?

Three short sentences, front-loaded with purpose, then endpoint reference, then the pagination constraint. No filler, though the bare API URL adds little for an agent that already has the schema.

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?

Output schema and annotations cover return shape and safety, and pagination is flagged, which is the main pitfall. For a 22-parameter list tool with nested summarize, the description still leaves pagination semantics (offset vs page interaction, default limit) and filter composition unexplained.

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 86%, so the schema carries the parameter documentation burden and baseline 3 applies. The description adds only one parameter-level insight — that summarize.all_pages aggregates over every page — leaving the 20+ filter params to 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?

States a specific verb and resource ('Retrieve a list of offers') and cites the underlying endpoint, so the agent knows this is a paginated read of offer records. It doesn't differentiate from near-neighbours like list_orders or get_offer_pdf, but the resource itself is unambiguous.

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 does give one explicit usage rule: one page per call, and points to summarize.all_pages when totals across all pages are needed. It gives no guidance on when to prefer this over list_orders or get_offer_pdf, or on how to combine the filter parameters.

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