Plan a loan ladder

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

Annotations already declare read-only, idempotent, non-destructive, open-world; the description adds the piece annotations cannot convey — that live mode requires the MUTEXA_ETH_RPC environment variable and fails otherwise. It also previews what the call reports (the band, extra collateral, and whether the single loan already exceeds max LTV), which reduces uncertainty about running it.

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?

Two sentences, no filler: the first defines the operation and output shape, the second gives the mode-selection rule and prerequisites. Mode selection is front-loaded in the second sentence where an agent will look for it before reading the schema.

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 an 11-parameter, no-output-schema tool the description covers the essentials (what it does, required inputs by mode, what it reports) but leaves the required 'placement' enum unexplained — an agent cannot know what 'around' vs 'beyond' does — and says nothing about the sibling plan_ladder's overlapping scope.

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 91%, so the baseline would be 3; the description earns above that by grouping parameters into mutually exclusive modes (live-reserve vs offline), which the flat schema cannot express. The gap is the required placement enum (around/beyond), which is left entirely undefined in both schema and description, and seed/sizeJitter are likewise only schema-documented.

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 concrete transformation on a specific resource: splitting one Aave V3 loan (one collateral, one debt, standard mode) into staggered-LTV loans whose liquidation prices form a band. That is far more than a restatement of the name. It does not, however, distinguish itself from the sibling plan_ladder, which the title ('Plan a loan ladder') makes easy to confuse with this tool.

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?

Explicitly splits usage into two modes and names the parameters that select each: collateralSymbol for live reserve data (with the MUTEXA_ETH_RPC prerequisite called out) versus ltv/liqThreshold/priceUsd for offline planning. No guidance is given on when to prefer this tool over the sibling plan_ladder or liquidation_map, so it falls short of a 5.

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