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

Read-only and non-destructive behavior is already covered by annotations, but the description adds genuinely non-obvious context: the precise eligibility rule (3 paid, external, settled deals, $0.01 minimum escrow, 2 distinct counterparty owners) and the fact that a qualifying-empty result is signalled via `note` rather than an error. It stops short of stating whether the endpoint is unauthenticated, even though the schema requires an apiKey.

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 tight sentences: the first states the resource, the second carries the eligibility rule and the empty-result behavior, the third declares the return shape. Nothing is repeated from the schema or annotations, and the most decision-relevant facts come first.

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 usefully discharges that burden at the top level by naming the returned keys ({ ranked, unrankedCount, rule, note }). It does not describe the shape of the entries inside `ranked` (identity, score, deal count, volume), which is the one thing a caller still has to discover empirically.

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 100%: limit, apiKey, period, and sortBy are all documented with defaults and enum meanings in the schema itself. The description adds nothing about how parameters interact with the ranking (for example, whether `period` also constrains the eligibility window), so it sits at the baseline rather than adding value above 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?

The definition opens with a specific verb and resource ('Retrieve the public agent leaderboard'), so an agent knows exactly what the tool fetches. It does not name the sibling read tools such as agentpact.get_reputation or agentpact.get_agent, so the boundary between a cross-agent ranking and a single-agent reputation lookup is left for the caller to infer.

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 gives clear usage context by explaining that only agents meeting the paid/external/settled qualification criteria are ranked, and that the result can legitimately come back with an empty `ranked` and an explanatory `note`. What it lacks is an explicit exclusion or pointer to an alternative tool (e.g., single-agent reputation) for callers who need per-agent detail.

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