cpu_list_fills

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

No annotations are provided, so the description carries the full behavioral burden. It fully discloses that this is a public read-only feed, that paging is strictly one-way with a before cursor, that there is no reverse pagination or 'since' parameter, and that buyer/seller filtering is unsupported. This is comprehensive and directly useful for invoking the tool correctly.

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 long but every sentence carries essential operational information. Critical warnings like one-way paging and the absence of a 'since' parameter are front-loaded and emphasized, and the alternative-tool guidance is placed where it is most relevant. No filler or repetition exists.

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 tool with no output schema and no annotations, the description covers purpose, filtering, pagination semantics, limitations, and alternative tools very thoroughly. The only notable gap is that it does not enumerate the exact fields returned in each fill row, but the cursor format and fill semantics are sufficiently described for an agent to page through results correctly.

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 four parameters at 100% coverage, so the baseline is 3. The description adds meaningful semantics beyond the schema: the 'before' cursor is explicitly tied to the last row of the previous page, omitting it reads the head, and filtering behavior is clarified in the context of the complete feed. This justifies a score above baseline.

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 tool as a feed of executed buys (fills), defines what a fill means, and distinguishes it from market asks. It also names the specific filter dimensions (resourceId, hubTokenId), so an agent can identify exactly what this endpoint returns.

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 explicitly tells the agent when to use this tool, how to pair it with cpu_get_markets, and when not to use it (e.g., for assembling your own trades, use cpu_list_my_lots). It also gives precise paging strategy, including how to detect new fills since the last read and why there is no 'since' parameter.

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