situation_stress_test

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

With no annotations, the description carries full behavioral burden. It discloses output signals (robustness, fragile_under), the perturbation vocabulary, and that it perturbs the world/position rather than advisor stances. But it never states whether it mutates persistent state or is a read-only simulation, nor permission/rate characteristics.

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?

Three tight sentences with no filler, front-loading the core purpose before the output and scope notes. Efficient, though the dense mixed-language phrasing slightly reduces immediate readability.

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?

A tool with nested objects, 0% param coverage, no output schema and no annotations needs more than this. The description partially compensates by naming return values and scope, but parameter shapes and state-mutation behavior remain unexplained, so it is not complete for the tool's complexity.

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 all 3 parameters are undocumented. The description hints that 'perturbations' maps to invalidate/weaken/inject_counter and that stance relates to 'позицию', but it gives no format, type, or shape for tree/stance/perturbations, leaving most semantics to inference.

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: an adversarial stress-test of the map/decision map, checking whether the line holds under world perturbations. It also names the perturbation operations (invalidate/weaken/inject_counter) and disambiguates from advisor-oriented siblings via 'НЕ уста советников'. Clear enough to distinguish from siblings, though the underlying object ('карта') is only loosely defined.

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 clause 'Возмущает мир/позицию, НЕ уста советников' gives an implicit when-not boundary, steering the agent away from stance/advisor perturbation. However, it names no alternative sibling (e.g. premortem, stability, validate_decision_map) and states no precondition or triggering context.

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