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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the added value here is the paywall gating (top 3 free, remainder paid) and the disclosure that fills and backing wallets are returned per market — both genuinely useful. However, key behavior is left opaque: how results are ordered, what the paid tier actually changes (truncation vs. access denial), and whether the divergence rule is evaluated per market or per side.

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 screening condition and followed by the access rule and a caveat — no filler. The final line ('A gap is not a call') is cryptic enough that it spends words without fully landing, which keeps it off a 5.

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 parameters and no output schema, the description carries the full burden of explaining the result set, and it only partially does so — 'the fills and wallets behind each' hints at structure but doesn't say what fields come back or how the ranking works. Since output schema is absent, the missing return-shape guidance is a real gap for a read tool an agent must interpret.

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 tool takes zero parameters, so there is nothing for the description to disambiguate and it correctly stays silent on inputs. Baseline of 4 applies; no parameter-level meaning is missing because no parameters exist.

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 a precise screening condition — markets where the GT line and Smart-money line diverge by 3+ points on the same side — and indicates the payload includes fills and wallets. It lacks an explicit verb (list? screen? rank?) and leans on undefined domain jargon, but the resource and filter condition are specific enough to separate it from siblings like line_check_board and pm_smart_money_entries.

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?

There is no statement of when to reach for this tool versus the sibling board or wallet tools. The one constraint given, 'Top 3 free; the rest paid,' is an access/monetization fact rather than usage routing, and 'A gap is not a call' is a disclaimer, not a when-to-use rule.

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