get_verdict

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

With zero annotations, the description carries the full burden of behavioral disclosure. It conveys that the tool is read-only in nature (it only fuses and evaluates) and is transparent about what it produces (a score, an enum, and a rationale) and that it makes a single tangentially aggregating call. It does not disclose any rate limits or data freshness caveats, but for a get-style tool the description is sufficiently open about the inner aggregation behavior.

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 exactly two sentences. The first sentence packs the purpose, the fused signals, and the output format, and the second sentence gives the usage trade-off. Every phrase earns its place; there is no repetition or 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?

Despite the conceptual complexity (composite of five signals), the description is complete for an agent to decide and call. It covers the input (one ticker), the output (score, enum, rationale), and the key trade-off with siblings, all in two sentences. An output schema exists, so the detailed return structure need not be repeated in the description. Nothing an agent needs to know before calling is missing.

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 0%, so the description must compensate for the single parameter. It adds 'one ticker' to the schema's bare `ticker` string, which clarifies the tool is per-ticker (not batch – other tools might accept multiple). However, it does not add formatting, validation, or example values. Given the extreme simplicity of the parameter, this is an adequate but not enriched compensation.

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 states a specific verb ('fuses') and resource ('composite verdict') for a single ticker, enumerates the exact inputs (trend stage, Point & Figure, insider-transaction clusters, macro regime), the output (score, accumulate/hold/distribute/avoid enum, rationale), and explicitly names the four alternatives when saying 'one call replaces separately calling stage, pnf, filings, and macro.' This leaves no doubt about what the tool does and how it differs from its siblings.

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?

It clearly tells the agent to use this tool when it needs a composite verdict and lists the sibling calls it replaces ('stage, pnf, filings, and macro'), providing a clear rationale for choosing get_verdict over them. It does not explicitly state when not to use it (e.g., when only a single underlying signal is needed), but the context is clear and the recommendation is direct.

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