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

Annotations already establish readOnly/idempotent/non-destructive, but the description adds real behavioral context: the 10-row/100K TVL/60-minute defaults, results sorted by largest TVL, rates expressed as fractions, and the caveat that stablecoin filters check labels rather than peg safety. It stops short of noting rate-limits or upstream feed lag beyond the freshness defaults.

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?

Three dense sentences, front-loaded with purpose and searchable dimensions, followed by defaults and the paging instruction. No filler or restated title.

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?

Output schema exists, so return values need not be explained, and the description covers filters, defaults and cursor paging. What is missing is sibling orientation (which of the six related tools to use instead) and any note about provider scope (pool-feed vs vault-feed) as a top-level concern.

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 repeats defaults that the schema already carries (limit 10, minTvl 100000, maxAgeMinutes 60, fraction-based APYs) rather than adding format or interaction semantics the schema lacks.

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?

Specific verb+resource ('Find DeFi yield pools') with the covered pool categories enumerated (lending, vaults, liquidity, staking) and an explicit statement of the return shape ('ranked table with pool ids'). An agent can distinguish this from get_pool, compare_pools and summarize_yields without opening a schema.

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?

It states when the query object can be omitted ('Omit for the whole catalogue') and how to page ('Page with the returned cursor'), plus the default result set. It never routes the agent to a sibling (e.g. get_pool for a known pool id, compare_pools for comparisons), so it falls short of true when/when-not guidance.

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