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

Annotations already cover read-only, idempotent, non-destructive, closed-world semantics, and the description adds genuinely new behavior: an auth/cost gate, the fact that signals are cryptographically signed, and an analytics-not-advice disclaimer. It does not discuss rate limits or result freshness/window, so not a 5.

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?

One dense sentence plus a bracketed premium banner, with the access requirement front-loaded before the capability statement. Every clause carries distinct information; nothing is redundant.

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?

Covers access, verification path, output contents, and the non-advice caveat, and an output schema already exists so return shape need not be spelled out. Remaining gap is the scoring window/horizon over which hit-rate is computed, which matters for interpreting the metrics.

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 single optional `type` parameter is fully documented in the schema at 100% coverage, including example values ('whale_net_flip', 'funding_apr'). The description adds nothing about filtering semantics, so it meets but does not exceed the baseline for high schema coverage.

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?

Names a concrete resource and enumerates exactly what is returned: per signal type, count, scored-against-forward-price count, hit-rate, and average/median direction-adjusted return. That is far more specific than a tautology, though it never distinguishes itself from the nearby hl_score_calibration or hl_signal_pubkey tools.

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?

Gives concrete preconditions: a premium tool that requires an API key, obtained via hl_request_free_key, or paid per call through x402. It also points at hl_signal_pubkey for verification. It stops short of saying when to pick this over hl_score_calibration, so no explicit alternatives/exclusions.

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