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

Annotations already declare read-only, idempotent, non-destructive. The description adds valuable context: fuzzy name matching returns best match plus close alternatives, and it discloses the price ($0.002 per call) and free tier. This goes beyond annotations and helps the agent assess cost.

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?

Concise five-sentence description. Front-loaded with the core purpose and data fields, then usage details, then pricing. No fluff.

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 single-parameter read-only tool, this is quite complete. Lists what data is returned, how to input the parameter, and pricing. Does not specify output format or error cases, but the data fields and fuzzy matching cover most agent needs. With no output schema, it could benefit from a note on response structure, but it's adequate.

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 has 100% coverage with 'name or slug' for the protocol parameter. The description elaborates with examples ('aave', 'Uniswap', 'jupiter') and explains the slug concept (DefiLlama slug), adding practical guidance. Also explains fuzzy matching behavior for the parameter.

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 exactly what it does: 'One DeFi protocol in depth' and enumerates specific data points (TVL by chain, trend, fees/revenue, market cap, audits, links). Distinct from siblings like defi_rankings or chain_tvl by focusing on a single protocol.

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?

Clearly implies when to use: for a single protocol's comprehensive profile. Mentions lookup by name or slug and fuzzy matching, but does not explicitly exclude other tools or state alternatives. Still, the context is clear enough for an agent to choose this over broader tools.

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