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

With no annotations provided, the description carries the full disclosure burden. It does add value beyond the schema by revealing the cost (0.01 USDC via x402), the cross-chain scope, and the exact return fields. However, it omits edge-case behavior such as what happens when no matches are found, and it does not explicitly state this is a non-destructive read operation — leaving the agent to infer safety from the word 'search'.

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?

Two efficient sentences with no wasted words. The purpose and return data are front-loaded in the first sentence, and the cost disclosure in the second adds specific value beyond the title's generic '(paid)' marker. Every sentence earns its place.

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 simple two-parameter search tool with no output schema, the description covers the core contract: search criteria, return fields, and cost. It is reasonably complete, but the 'limit' parameter semantics are entirely unaddressed in both schema and description, and there is no guidance on edge cases like zero matches or pagination behavior. Missing those leaves the agent partially uninformed when invoking the tool.

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 50%: the 'query' parameter is documented in the schema ('token name or symbol, e.g. pepe or coinbase'), matching the description's phrasing. The 'limit' parameter has no schema description and the tool description does not compensate — it never explains that limit controls how many matched pairs are returned, though 'highest-liquidity matched pairs' loosely implies result selection. Partial compensation but a clear gap remains for the limit 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?

The description states a specific verb and resource: 'Search crypto tokens by name or symbol' and specifies the return data (highest-liquidity matched pairs with price, liquidity, FDV and 24h volume across chains). This clearly distinguishes the search/match behavior from sibling get_token_price, which likely does a direct single-token lookup. The purpose is clear and specific, though it doesn't explicitly contrast itself against get_token_price.

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 use case is only implied — search tokens by name/symbol — but there is no explicit statement of when to use this tool versus the sibling get_token_price, nor any exclusions. The payment disclosure ('Cheap per-call market lookup') hints at a cost consideration but never tells the agent how to choose between search_tokens and a direct price lookup. No when-not-to-use guidance is present.

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