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

With no annotations, the description carries the full burden of behavioral disclosure. It transparently describes the calculation approach, including how different protocols are attributed and that Aave is deliberately left unattributed. It also states it is 'Measured live' and clarifies it is not a correlation estimate. Minor gaps: it does not mention authentication, rate limits, or whether this is a read-only operation, but the overall behavior is well described.

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 front-loaded with a concise summary sentence, but then expands into multiple long illustrative examples and narrative details. While every part contributes to understanding the tool's purpose and nuances, the length is excessive for a simple 'what it does' explanation. It is well-structured (definition, example, attribution rules) but could be tightened by reducing the Stream Finance anecdote.

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?

There is no output schema, so the description must compensate. It explains what the tool returns (per-factor capital exposure, venues, attribution) and gives concrete percentage examples. However, it does not describe the exact structure of the output (e.g., list of factors, keys, format). Given the tool's complexity, the description covers the key concepts but leaves some ambiguity about the precise response shape.

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 description coverage is 100%, so the baseline is 3. The description adds some conceptual context (e.g., what 'positions' mean and examples of known protocols) but does not go beyond what the schema already documents for each parameter. The 'asset' parameter is not mentioned in the description, but the schema already explains it clearly. Thus, the description adds marginal value over the schema.

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 uses a specific verb ('returns') and resource ('shared risk exposure across a declared portfolio'), and immediately clarifies the input format. It distinguishes itself from sibling tools by framing the question as 'the question the market does not answer' and explicitly saying 'Structural shared exposure, not a correlation estimate.'

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 provides clear when-to-use context: it addresses whether you are 'two hops' from an event, gives a real-world example (Stream Finance collapse), and explains how to feed positions. It also includes important computational caveats (Morpho per isolated market, Compound by collateral basket, Aave unattributed), which act as usage guidelines for interpreting results. No explicit 'when not to use' is stated, but the positioning against correlation estimates and alerts serves as an implicit exclusion.

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