find_alpha

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

No annotations are provided, so the description carries the full burden. It transparently discloses what the tool returns (ranked opportunities with discount percentage, estimated value range, confidence rating, comparable data) and emphasizes its 'edge' as finding mispriced names. It does not explicitly state it is read-only, but 'scan' and 'returns' imply no side effects. Lacks details on data freshness or potential lag, but the confidence rating offers some behavioral context. This is solid but not exhaustive.

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 somewhat lengthy but front-loaded with the core value proposition, then explains return fields and usage. The bolded directive is clearly separated and high-signal. Every sentence contributes useful information (what, why, when, how to filter). It could be tightened by removing the 'agent's edge' marketing language, but it is not bloated or redundant. A strong structure with minimal waste.

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?

Given that the tool has 7 parameters and no output schema, the description is quite complete. It explains the return format (ranked opportunities with discount, value range, confidence, comparables), lists relevant filters, and gives usage context. It does not enumerate every parameter, but the schema covers those. It could mention the sort order of results (implied by 'ranked') or any pagination behavior, but for an alpha-scanner tool, this is sufficient for an agent to invoke it correctly.

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 baseline is 3. The description adds value by illustrating combined filters with an example ('4-letter names under 1 ETH, best value'), but it also mentions 'tags' as a filter even though the schema does not include a 'tags' parameter. This is a minor inconsistency that prevents a higher score. Overall, the schema already explains parameters well, and the description adds marginal context with a slight error.

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 states the tool's purpose with specific verb+resource: 'Scan the ENS marketplace for alpha — names listed below their comparable-sales valuation.' It distinguishes itself from sibling tools like search_ens_names and get_valuation by explaining it does both search and valuation in one call, returning ranked opportunities. This is a specific, action-oriented purpose that leaves no ambiguity.

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?

Excellent guidance: explicitly tells when to use this tool instead of alternatives: 'Use this instead of search_ens_names + repeated get_valuation when the user asks for "best value", "best buy", "cheapest good name", "undervalued", "bargains", or any ranked-by-value query across multiple listings.' It also mentions 'Pair with get_valuation for deep analysis, then purchase_name to execute.' This gives clear context and exclusions.

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