council_verdict

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

With no annotations, the description carries the full burden and does so well: it discloses read-only, zero-LLM, code-computed behavior, enumerates output components (scores, dispersion, council confidence, overrides, missing), and names override triggers (ruin ceiling, irreversibility under split, unanimity anxiety, WAIT). It also clarifies that errors are surfaced as council questions. It stops short of stating auth or rate 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?

Purpose is front-loaded ahead of the output and parameter details, and the arrow-separated clauses keep it information-dense rather than padded. It is still a single heavy paragraph, which makes the later clauses harder to scan.

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 tool with 3 params, nested objects, no annotations, and no output schema, the description usefully substitutes for the missing output schema by listing return components and override behaviors. It remains incomplete on the nested scorecard shape and the lang parameter.

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 coverage is 0%, so the description must compensate. It documents track_weights semantics (advisor_weights output as-is, multiplier clamped 0.5..1.5) and sketches scorecard contents (per-advisor scores 0..10, lens weight 1..3, confidence 1..5, ruin_risk, door, change_my_mind, question_for_user). The required nested scorecard structure and the lang enum are not explained, leaving a real gap.

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?

States a specific verb+resource ('вердикт совета по scorecard') and qualifies it precisely as read-only, zero-LLM, code-computed. It enumerates the output labels (ИДТИ / ИДТИ С УСЛОВИЯМИ / ПЕРЕДЕЛАТЬ / НЕ ДЕЛАТЬ / ЖДАТЬ), clearly distinguishing it from verdict-adjacent siblings like gate_verdict.

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?

Sequencing guidance is present ('после форума по вопросу-решению'), which implies when to call it. However, no alternative tool is named and no explicit when-not condition is given (e.g., vs gate_verdict or advisor_weights), so usage is implied rather than routed.

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