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

Description declares 'Read-only; no wallet signing, broadcasting, or custody' which covers external side effects, but lacks explicit statements about in-memory state mutation, though 'read-only' implies no state changes. No annotation exists to add credibility.

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?

Compact but dense description. It is structured with use-cases, alternatives, read-only note, template list. Not wordy, but rich.

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?

The output schema exists, and the description includes plan components (bounded asset amount, stressed health, evidence basis, ERC-20 approval plus Morpho stack). Context is given through sibling tool references and output/input schema, sufficient for a read-only calculation tool.

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?

Parameter descriptions in the schema are substantive: address pattern, basis-point buffer meaning with default and range, target health with exclusive min and max, and collateral shock range with -10 example. No parameter details are in the description, but schema coverage is 100% and the encoding is clear.

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+resource ('Calculate two alternative protection plans for one Base Morpho borrower under a selected collateral-price shock and target health') and explicitly differentiates from sibling tools by naming the alternatives (morpho_position for diagnosis, morpho_market_underwrite for market-wide risk, morpho_preliquidation_replay for historical events).

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?

Provides explicit when-to-use guidance ('Use `morpho_position` for a diagnosis without a plan, `morpho_market_underwrite` for market-wide risk, or `morpho_preliquidation_replay` for a completed historical event') and states read-only constraints, wallet signing, broadcasting, custody.

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