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

Beyond the readOnlyHint annotation, the description reveals the algorithm (embedding cosine similarity), the ranking behavior, the valid k range (1-20), the requirement to supply at least one of coin/q, and the non-advice disclaimer. It also notes the REST mirror, adding valuable context about how the tool behaves without contradicting the annotations.

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 compact and front-loaded, using a single well-structured sentence that combines a memorable label, a clear mechanism, parameter constraints, a practical example, and a disclaimer. Every phrase adds value, and there is no unnecessary filler.

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 read-only search tool with no output schema, the description covers the purpose, input constraints, algorithm, and use case. It could be more explicit about the return structure (e.g., whether the output includes similarity scores), but the phrase 'get the k most similar past signals ranked by embedding cosine similarity' gives a sufficiently clear picture of the result.

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?

With 0% schema description coverage, the description compensates by explaining the role of k (number of similar signals, 1-20, default 5), q (free-text query), and coin (a coin). It also adds the constraint that at least one of coin/q must be provided. However, it does not specify the exact format for coin (e.g., symbol vs. name) or the query syntax, leaving some ambiguity.

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 a specific action: 'Semantic similarity search across the signal corpus' and describes the resource (past signals) and the output (k most similar ranked by cosine similarity). The 'DRILL-DOWN — history rhymes' label and the phrase 'have we seen this setup before' help distinguish it from sibling tools that retrieve individual signals or market analogs.

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 clear usage context through the exploratory question 'have we seen this setup before and what did it look like' and states the required input ('Provide at least one of coin / q'). However, it does not explicitly name alternative tools or state when not to use this tool, so it falls short of full guidance.

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