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 behavior. It states clearly that the tool returns 'the endpoints that cover it, with their price and parameters,' which sets expectations for output structure and scope. It also enumerates covered asset classes (Brazil, US equities, forex, etc.) and includes examples that hint at query handling (e.g., 'is this Solana token a rug pull'), which discloses some interpretation behavior. However, it does not mention read-only guarantees, error cases, or query limits, though these are less critical for a search tool.

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 highly scannable, opening with an attention-grabbing 'FIRST STEP' followed by a clear one-sentence summary. The list of coverage areas and examples are useful but slightly long, making it a bit verbose for a tool description. Overall, it is well-organized and every sentence adds value, though some examples could be trimmed without loss.

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 search/discovery tool with no output schema and no annotations, the description provides sufficient context for an agent to invoke it correctly: it explains what to input, the expected response (endpoints with price and parameters), and the supported domains. It does not detail the response format for endpoints (e.g., JSON structure) but given the tool's role as a router, this level of detail is adequate. The absence of output schema is compensated by the explanatory text.

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?

The input schema already provides clear descriptions for both parameters ('query', 'limit'), giving 100% coverage. The description goes beyond the schema by offering realistic query examples and clarifying the expected style of input ('in plain language'), which helps an agent formulate effective queries. The limit parameter is not explicitly addressed in the description, but the schema covers it, so the baseline of 3 is elevated by the practical examples.

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 as the 'FIRST STEP for any market-data question,' with a specific verb (search) and resource (market data), and explains it returns endpoints with price and parameters. It differentiates from siblings by positioning itself as the entry point for discovery. The inclusion of specific coverage areas and multiple plain-language examples leaves no doubt about its function.

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 phrase 'FIRST STEP' implies usage as a starting point, but the description does not explicitly state when to prefer this over siblings like get_market_data or market_snapshot. There are no exclusionary criteria or alternative-route guidance for an agent that already has an endpoint ID and needs raw data. The usage context is implied through examples but not directly contrasted with alternatives.

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