diversity_check

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

With no annotations, the description carries the full burden and does disclose the key traits: read-only, the 0..1 output scale, the duplicate threshold, and the follow-up action on a low score. It does not cover edge behavior (empty/single-advisor lists, error handling) or performance, but for a local read-only analysis tool the disclosure is solid.

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, then the mandatory-usage rule and thresholds; two dense sentences with almost no filler. The parenthetical metric list is information-packed rather than wasteful, though the sentence is long enough to be slightly hard to parse.

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?

Covers the missing output schema by describing the return values (diversity score, dup flags, uncovered axes) and supplies the decision threshold and required next action. The remaining gap is the undocumented advisor_dirs format, which the description should have specified given 0% schema coverage.

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% and there is a single parameter, advisor_dirs, whose array-of-paths format is never explained in the description. The phrase 'состав совета' implies these are the advisor directories to be evaluated, so the meaning is inferable, but no format, expected structure, or minimum count is given.

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 (checks orthogonality of council composition) and enumerates exactly what it computes: diversity 0..1, duplicate-voice detection (similarity >= 0.5 → flag=dup), and uncovered thinking axes. Neither the resource nor the output metrics could be confused with any sibling such as board_status or council_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?

'ОБЯЗАТЕЛЬНО перед созывом совета (правило 18в)' gives an explicit mandatory trigger plus the interpretation rule (diversity < 0.5 = echo chamber → warn user, propose a counter-voice). It is very clear on when to call it, but never names an alternative tool or a when-not condition, so it stops short of full routing guidance.

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