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

With no annotations, the description carries full responsibility for behavioral disclosure. It discloses the cost ($0.05 per call), explains payment mechanisms (x402 or API key), and adds the disclaimer 'Educational data, not financial advice.' It does not explicitly state read-only, but that is inherent. It also mentions output nature (counts and average confidence), which is beyond annotations. This is solid behavioral context, though it could mention rate limits or response format.

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 fairly long, including cost, function, payment instructions, and disclaimer in a single paragraph. It is front-loaded with cost and function, which is good, but the payment details add length. While every sentence serves a purpose, it could be more concise by separating payment info into a clearer structure. It is not terse, but it is organized. A 3 reflects the slight over-length.

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 one parameter and no output schema, this description is quite complete. It explains the output shape (bullish/bearish counts and average confidence), covers payment and authentication, and references get_catalog for broader context. It lacks example symbol format but overall provides sufficient context for an agent to use the tool correctly. A 4 is appropriate.

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 schema has a single required 'symbol' parameter with 0% description coverage. The description says 'for one symbol' and implies the symbol is needed, but does not specify format (e.g., ticker, case-sensitivity). For a single obvious parameter, this is adequate, but it does not add much beyond the schema's parameter name. Given the simplicity, a 3 is fair.

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: 'composite signal read for one symbol: latest 50 signals across all generators merged into bullish/bearish counts and average confidence.' This is specific (verb: get/read, resource: composite signal, scope: one symbol) and differentiates it from sibling tools like get_signals or get_symbol_sentiment by emphasizing it merges all generators. The phrase 'flagship per-symbol conviction snapshot' further cements its unique role.

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 implies when to use it—as the flagship per-symbol snapshot—but does not explicitly contrast with alternative tools. It advises browsing all tools via the free get_catalog tool, giving users a path to discover alternatives. However, it lacks explicit 'when not to use' guidance, though the positioning is clear enough. It earns a 4 for providing context and pointing to catalog.

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