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

Annotations already cover read-only and open-world safety, but the description adds real behavioral detail: outliers and APY > 200% are dropped, stablecoin-only default kicks in when no asset is given, and each pool carries APY split base vs reward, TVL, risk notes, a DefiLlama link and a swapIntoUnderlying link. No pagination, freshness, or sourcing-latency notes, so not a 5.

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?

Front-loaded with what the tool returns and how it filters, which is the highest-value information. The trailing instructions (offer a swap next, show the `display` markdown, see swapchan_playbook) are useful but read as several appended sentences rather than an integrated structure.

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?

With no output schema and only 20% param coverage, the description carries the burden and largely meets it by itemizing returned fields, default filtering, and the intended follow-up action. Still missing: what `limit` controls, what the default/cap result count is, and which chains 'SwapChan's chains' actually spans (though get_supported_chains exists).

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 only 20% (chainId alone is documented), and the description compensates well by explaining asset semantics, the min-TVL default of $1M, and the stablecoinOnly default behavior. The `limit` parameter is left entirely undocumented in both schema and description, so it does not fully close the gap.

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 resource (top yield pools aggregated from DefiLlama) across SwapChan's supported chains, plus the key filter dimensions, so an agent can distinguish it from token_pools and scan_* tools. It stops short of explicitly naming which sibling to use instead when the user wants a single token's pools.

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?

Gives concrete when-to-use context: after surfacing a pool, follow with get_quote / the swapUrl, and it points to swapchan_playbook for the broader workflows. It does not state when NOT to use it (e.g. 'for a single known token use token_pools'), so it falls just short of full routing guidance.

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