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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered; the description adds the parts annotations cannot express: cursor exclusivity ('strictly after'), ordering, the implicit one-hour lookback window, and the next/more pagination contract. It does not describe rate limits or the shape of a fill record, keeping it out of 5 territory.

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 the resource/scope, then default window, then pagination. Every sentence carries information an agent needs; phrasing is slightly telegraphic but not padded.

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 does the necessary work of naming the returned `next` and `more` fields and the loop that consumes them, and annotations carry the safety profile. It leaves unspecified what fields an individual fill contains, which is a minor gap for a read-only list tool.

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 100% and the schema already documents limit defaults/max, so the baseline is 3. The description goes beyond it by clarifying that sinceBlock is an exclusive cursor, that sinceLogIndex pairs with it, and that omitting sinceBlock yields a default recent window — meaningful additions over the terse schema text.

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 names the specific resource (fills), the scope (of followed traders only), and the ordering (oldest first), which is enough for an agent to distinguish this from siblings like leaderboard, account, or market. It never explicitly contrasts itself with a sibling, but the resource scope is precise enough that no confusion is likely.

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 states the default behavior when sinceBlock is omitted ('from about one hour ago') and gives explicit pagination procedure ('pass the returned `next` back', 'call again at once while `more` is true'), which is real operational guidance. It does not name an alternative tool or a when-not-to-use condition, so it stops short of a 5.

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