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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it exceeds that burden. It details how the tool attributes exposure per protocol, uses live data ('Measured live'), and even explains why Aave is reported unattributed (splitting would imply non-existent diversification). It also highlights the tool's unique value proposition (two-hop contagion) and its limitation (not a correlation estimate). This is rich behavioral context beyond what any schema or annotation could provide.

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 longer than most, but it is well-structured: a clear definition, a vivid motivating example, and a concise methodology section. The Stream Finance anecdote is illustrative but arguably non-essential; the final sentence 'Structural shared exposure, not a correlation estimate' is a strong close. It is front-loaded with the core purpose, and every remaining sentence adds meaningful context. It is slightly overlong but never redundant.

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 the tool's complexity, no annotations, and no output schema, the description is remarkably complete. It covers the core inputs, the methodology per protocol, the rationale behind those methodologies, and concrete examples that clarify expected output. It does not describe a return schema, but the description's phrase 'per factor, how much of your capital sits behind...' gives enough shape. The tool's limitations and boundaries are also disclosed, making it fully contextualized for an agent.

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 schema already covers both parameters with 100% coverage, each having a clear description and example. The tool description does not add significant meaning to individual parameters; it mentions the positions format ('protocol:usd pairs') but the schema already does. The conceptual explanation of how capital is mapped to risk factors is valuable but not parameter-specific. Given the high schema coverage, a baseline 3 is appropriate, and the description's marginal contribution does not push it higher.

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 states the tool's function: 'Shared risk exposure across a declared portfolio' and 'returns, per factor, how much of your capital sits behind the same collateral, price oracle or vault curator.' It uses a specific verb ('returns') and resource ('shared exposure'), and the examples ('Morpho USDC vault... 93.7% behind cbBTC vs Compound's 43.1%') make the purpose unmistakable. It also implicitly distinguishes itself from sibling tools (exit capacity, rate sensitivity, yield signals) by focusing on structural risk rather than yield or liquidity.

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 explicitly tells when to use this tool: 'This is the question the market does not answer: depeg and hack alerts tell you an event happened, not whether you are two hops from it.' It also tells when not to use it: 'Structural shared exposure, not a correlation estimate.' The methodology section explains the treatment of each protocol (Morpho per isolated market, Compound by posted collateral, Aave unattributed), giving clear guidance on what to expect and how to interpret results.

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