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

With no annotations supplied, the description carries the full burden and does well: it discloses the upstream source (Hyperliquid /info), that data is live with a 30s cache, the ~180-coin breadth, the included top-5 funding extremes and chain-wide OI/volume totals. It stops short of stating rate limits, error behavior, or pagination/response envelope, but the operational profile is unusually well communicated for an un-annotated read tool.

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 field inventory is front-loaded, which is good, but it is delivered as one dense run-on sentence with a second sentence that is cut off mid-word ('funding-harvest sc'). The truncation is a real defect that leaves the usage guidance incomplete rather than concise.

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?

Because there is no output schema, the description correctly spends its words enumerating returned fields, the sort modes, the 30s cache and the top-5 extremes — that is close to sufficient for a snapshot tool. However, the schema/description mismatch on filter-sort-limit parameters and the truncated closing guidance leave the definition incomplete on exactly the points an agent must act on.

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 input schema declares zero properties with additionalProperties:false, yet the description instructs the agent to 'Filter with ?coins=BTC,ETH', 'sort with ?sort=volume|funding|oi|change|name' and 'cap with ?limit=1-300'. These query-style parameters do not exist in the schema, so an agent following the description will attempt arguments the tool rejects. The documented ranges and enum values are otherwise useful, but the mismatch makes the parameter story actively misleading.

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 gives a very specific verb+resource: a Hyperliquid perpetuals market snapshot listing exactly which fields are returned (mark/oracle price, premium bps, funding rate 8h + APR, OI, 24h volume/change, max leverage). An agent knows precisely what data this produces. It loses the top score because it never differentiates itself from the clearly overlapping siblings akari_hl_market and akari_funding_edge, and the closing guidance is truncated mid-sentence.

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?

The only when-to-use signal is the truncated fragment 'Use for funding-harvest sc…', which implies a screening use case but gives no complete condition and no exclusions. There is no statement of when to prefer a sibling (e.g. akari_funding_edge) over this snapshot, so an agent must infer selection from the field list alone.

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