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

With no annotations to rely on, the description carries the full behavioral burden. It discloses that the score captures slippage only, that high scores can coexist with high revert rates, and that execution quality varies across chains. It does not detail output shape or data freshness, but the core behavioral caveats are clearly surfaced.

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 well structured and front-loaded: the core definition comes first, followed by essential caveats and chain guidance. It is slightly repetitive with the schema's warning about not describing the blend as one chain's result, but every sentence earns its place and the warnings are important.

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 a low-complexity tool with two optional parameters, no required inputs, and fully documented schema fields, the description is complete. It explains what is measured, how scores are expressed, what is deliberately excluded, when to use the sibling revert_rates tool, and how the chain parameter affects the result. No critical invocation detail is missing.

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 value beyond the schema by explicitly framing the chain parameter as a choice between 'single-chain ranking' and 'blended cross-chain rollup,' with the rationale that execution quality is not uniform across chains. The limit parameter is already fully documented in the schema, including clamping behavior and the context-window rationale.

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 opens with a specific verb and resource: 'Rank DEXs and aggregators by realized execution quality: median slippage against a 1-minute VWAP baseline.' It defines the score scale and differentiates the metric from revert rates and MEV exposure, making it distinct from the sibling revert_rates 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?

The description explicitly warns this is not an overall best-execution ranking, states that revert rates and MEV are separate metrics, and directs the caller to revert_rates for that information. It also gives chain-mode guidance: pass a chain for single-chain ranking or 'all' for the blended rollup, with a clear caveat not to misrepresent the blend as a single chain's result.

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