Raw Fills

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

Annotations already declare readOnly/openWorld/non-destructive, and the description adds real behavioral detail: the output is the unchanged indexer tape, newest first, with a 1000-fill cap, and it enumerates the per-fill fields including position context. This goes well 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 purpose, then packs the field list, ordering, cap, address provenance, and an example into compact high-signal sentences. No filler or repetition.

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 an output schema present and annotations covering the safety profile, the description supplies nearly everything else: purpose, alternative tool, sort order, cap, field contents, and address source. The only meaningful gap is the semantics of the optional subaccount parameter.

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 0%, so the description must compensate. It partially does: 'limit capped at 1000' defines the limit parameter, and the example plus address-source guidance clarify address. However, the optional subaccount parameter is only mentioned narratively as 'for a subaccount' and its integer/default behavior is never explained.

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 says exactly what the tool returns: the raw execution tape for a subaccount, 'every field the indexer gives, unchanged'. It also distinguishes itself from fills_review by noting the aggregated view lives there, so there is no sibling-confusion.

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 scopes usage to agents doing their own execution-quality math and points to fills_review as the aggregated alternative. It also tells where valid addresses come from (discover_traders / leaderboard / list_traders), though it does not give an explicit when-not-to-use directive.

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