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

Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds value by saying results are 'informational only' and that they 'carry provenance,' and it discloses the output content (strength, numbers, consensus). This is useful context beyond the annotation flags, though it does not cover errors or rate limits.

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 cover purpose, signal types, output content, filtering, safety, and provenance without redundancy. The information is front-loaded and every sentence earns its place.

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?

For a read-only tool with optional filters and no output schema, the description explains what the result contains (strength, numbers, consensus, provenance) and how to constrain it. It is complete enough for an agent to invoke it, though a bit more detail on the returned structure would be ideal.

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 67%, with bias and coins documented but limit lacking a schema description. The description's phrase 'Filter by coins or bias, cap with limit' adds meaning for all three parameters)Skip and directly compensates for the undocumented limit parameter. It is concise but sufficient.

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 clearly identifies the tool's output: rules-based setups on Hyperliquid perps with strength, underlying numbers, and a long/short consensus. It distinguishes the tool from siblings by naming specific signal types (funding carry, premium dislocation, momentum), though it lacks an explicit verb like 'returns' or 'lists'.

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 description gives operational guidance by saying 'Filter by coins or bias, cap with limit,' and marks it as informational only. However, it does not state when to prefer this tool over siblings like tape_live_alerts or tape_market_pulse, nor does it provide any exclusions or conditions for alternative tool selection.

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