Skip to main content
Glama

Audit a Blend lending pool against Keel

audit_blend_pool
Read-onlyIdempotent

Audits Blend V2 pool collateral configuration by comparing each reserve with Keel's maximum safe size and Stellar liquidity, flagging holdings or accepted amounts that exceed absorbable liquidity.

Instructions

Reads a Blend V2 pool's collateral configuration from Stellar (collateral factor, supply cap, total supplied, oracle price) and sets each collateral reserve beside Keel's maximum safe collateral size for that asset. Says per reserve whether what the pool HOLDS and what it would ACCEPT exceed what Stellar liquidity can absorb. Omit pool to audit every known pool (YieldBlox, Fixed). Read-only; state the interpretation notes with any conclusion.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "audit_blend_pool"
  }
}

Input Schema

NameRequiredDescriptionDefault
poolNoA known pool name (YieldBlox, Fixed) or a Blend pool contract id. Omit for all known pools.
withOraclePricesNoAlso read the pool oracle price per asset and compare it with Keel. Default true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, open-world; the description adds that data is read on-chain from Stellar and that omitting pool triggers a fan-out across all known pools, plus an output obligation to state interpretation notes. It does not cover failure modes for unknown pool names or rate/scale costs of the all-pools sweep.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the read operation, then the comparison semantics, then the all-pools default and the read-only caveat; no filler sentences. The phrasing is dense and slightly elliptical ('what it would ACCEPT'), costing a little clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-shape burden and does so by describing the per-reserve verdict format. The main residual gap is error behavior for an unrecognized pool name or contract id, which an agent would need before calling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents both parameters, and 'Omit for all known pools' largely restates the pool description. The description does add meaning for withOraclePrices by explaining the oracle price is compared against Keel, but the default-true behavior is already in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource (reads a Blend V2 pool's collateral configuration from Stellar) and specifies the exact composite result: each collateral reserve placed beside Keel's maximum safe collateral size, with a verdict on whether held/accepted amounts exceed Stellar absorbable liquidity. That level of detail distinguishes it from single-asset siblings like check_collateral_size.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an operational rule for the pool parameter (omit to audit all known pools: YieldBlox, Fixed) and a read-only framing, but never states when to prefer this over check_collateral_size, compare_assets, or keel_status. Usage is implied by the auditing scenario rather than explicitly routed.

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