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

With no annotations to rely on, the description carries the full burden and excels: it details deduplication logic, role-based weighting, direction inference rules (CALL@ASK=+1, etc.), metadata mode for fundamental, the 'EVIDENCE rather than a number' output philosophy, and a 15min cache. This is rich behavioral disclosure.

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 dense paragraph, but every sentence contributes useful information. It front-loads the purpose and then provides detailed operational specifics. While a bulleted structure might improve readability, the content is appropriately sized for the complexity.

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 complex 3-parameter tool with no output schema or annotations, the description covers a lot: voter modes, calculation logic, output philosophy, pending voters, and cache. Gaps include unspecified behavior for unsupported voters and limited elaboration on days_back semantics, but these are minor given the overall detail.

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 only documents the ticker path parameter. The description adds complete enumeration for voter (insider_flow|options_flow|fundamental) with detailed operational meaning for each, and provides a default example for days_back (?days_back=30). This significantly compensates for the low schema coverage, though days_back semantics are implied rather than fully specified.

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 opens with 'Causal attribution for a voter's score on a ticker,' a specific verb+resource statement. It enumerates the three instrumented voters and explains the transformation of scores into evidence, distinguishing it from sibling tools like voter_coverage or voter_ic_drift.

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 clearly states which voters are supported and explicitly notes that remaining voters are 'pending instrumentation,' providing an exclusion. It also mentions optional parameters (?voter, ?days_back) and cache behavior. However, it does not explicitly name alternative tools for other use cases, though the context is fairly clear.

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