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

No annotations are provided, so the description carries the burden. It clearly discloses that the tool is a read-only data access ('Call this to read'), describes the calculation source (mark vs oracle/index), and explains interpretation. It also adds interpretation guardrails ('never directional on its own'). It doesn't describe pagination or exact response fields, but for a context metric the core behavior is disclosed.

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?

Four compact, information-dense sentences. Every sentence earns its place: what it reads, how it is denominated, how to interpret positive/negative, and explicit guardrails. No filler or redundancy.

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 context metric with no output schema, the description provides the metric's meaning, interpretation, and guardrails. The main gap is the undocumented 'symbols' parameter — the agent must infer the format. It is otherwise complete against a large sibling set because it clearly defines its unique metric.

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 0%, so the description should compensate. It explains what the tool returns but does not document the 'symbols' parameter format or the 'asset_class' enum. The schema itself only shows symbols as a string with no format guidance, leaving the agent to guess. The description adds no parameter-level detail beyond the tool's purpose.

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?

States a specific verb ('read') and resource ('CARRY — perpetual premium (mark vs oracle/index) in basis points per venue and the cross-venue mean'). Clearly defines positive/negative values. Distinguishes itself from siblings like funding, open interest, and vol surface by naming the specific metric.

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?

Describes the metric's meaning and explicitly warns it is a 'context flag, never directional on its own' and 'not_a_score, not_a_forecast.' This gives clear guidance on how to interpret and apply the data. However, it does not explicitly name sibling alternatives or state when to use a different derivatives tool.

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