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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the tool is known to be a safe, read-only, idempotent operation. The description adds valuable behavioral context beyond the annotations: it labels the outputs as 'deterministic,' describes the per-ticker data included, and explicitly warns 'Signals are NOT orders,' which helps prevent misuse. This exceeds the baseline expected when annotations are present, though it could still mention behavior like absence of results or pagination.

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 description is compact yet information-dense. It front-loads the core purpose, then lists the output fields with explanations, and ends with a parameter filter and a safety note. Every sentence adds value; there is no filler or repetition. Despite being a single long sentence for the outputs, it is well-structured with em-dash separators and remains readable.

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?

Given a read-only tool with one optional parameter and no output schema, the description provides a complete picture: it explains what the tool returns (per-ticker funding rate, APR, basis gap, carry label, risk flags), how to filter the results, and that signals are not orders. It does not require a return schema because the output fields are explicitly described. The only minor omission is the exact composition of 'standard risk flags,' but this likely follows the platform-wide convention and is not a critical gap.

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 only provides the parameter name, type, and default (min_abs_bps: number, default 0), with no description. The tool description directly explains the parameter's purpose: 'min_abs_bps filters on |perp_vs_chainlink_bps|.' This fully compensates for the 0% schema description coverage, giving the agent clear guidance on how to use the parameter.

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 specifies exactly what the tool produces: deterministic funding-carry candidates that combine perp funding rates with perp-vs-spot basis. It details the output fields (funding rate, funding APR, basis gap, carry label) and clearly distinguishes from order execution with 'Signals are NOT orders.' This goes beyond a simple verb+resource and effectively differentiates from sibling tools like perp_funding and perp_spot_basis by describing the combined analysis.

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 clearly implies when to use this tool: when you need deterministic funding-carry candidates that merge perp funding and basis data. It also states what it is not (orders), which helps avoid misuse. However, it does not explicitly name alternative tools or state exclusions, so it falls short of the 'explicit when/when-not/alternatives' bar for a 5.

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