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

With no annotations provided, the description carries the full burden of disclosing behavioral traits. It does not mention whether the operation is read-only, any rate limits, data range limitations, or the structure of the returned candles (e.g., whether volume is included). The description is purely declarative and does not cover safety or side-effect implications. While the tool is likely safe, the absence of any such disclosure makes it hard for an agent to assess trust or handle unexpected responses.

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 a single, straightforward sentence that front-loads the core purpose ('OHLCV candles') and immediately specifies the token selection rule. The timeframe list is appended efficiently without fluff. Every word earns its place; there is no redundancy or unnecessary detail. This is an exemplar of concise writing for a simple data-fetch tool.

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 tool with only 3 parameters and no output schema, the description covers the essential purpose and the main selection criterion. However, it omits a few pieces that would strengthen completeness: it does not explicitly state what the response contains (candles with OHLCV, timestamps, etc.), whether there are pagination limits, or how historical depth is determined. It also does not mention that the tool is read-only, which for a charting tool is a notable behavioral gap. Overall, it is adequate for a basic call but falls short of fully equipping an agent to handle edge cases or validate results.

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 low (33%), as only the timeframe parameter has a description in the schema. The tool description compensates partially: it explicitly lists the supported timeframes, which adds semantics beyond the enum, and it clarifies that the address refers to a token and that the pool is chosen by top liquidity. However, it does not explain the 'chain' parameter beyond the enum names, nor does it hint at the expected format for the address (e.g., checksummed contract address). The added value is present but not fully compensatory for the schema gaps.

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 clearly identifies the tool's function: retrieving OHLCV candles for a given token on its top liquidity pool. It specifies the resource (token) and the selection scope (top pool by liquidity), and it also lists the available timeframes. This distinguishes it from the trading-focused sibling tools like build_swap_transaction and get_swap_quote, which serve different purposes. The verb 'get' and the explicit 'OHLCV candles' convey the exact action.

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 provides no guidance on when to use this tool versus alternatives. It does not mention any conditions, prerequisites (e.g., token address format), or scenarios where one might prefer another tool. The only useful context is the implied 'if you need chart data, use this,' but there is no explicit comparison or exclusion. For a tool that likely sits alongside many trading operations, this omission leaves an agent to infer selection criteria from the purpose alone.

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