design_audit

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

Annotations already state readOnlyHint=false, idempotentHint=false, destructiveHint=false, and the phrase 'reverts' is loosely consistent with the non-destructive hint. However, with no output schema and no explanation of what the perturbation measures, whether state is fully restored on failure, or what the results look like, the behavioral picture is largely opaque. It neither contradicts nor meaningfully enriches the annotations.

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?

It is a single short sentence with no waste, but brevity here is under-specification rather than conciseness — nothing is front-loaded because there is essentially no content to structure.

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 two-parameter tool with 0% schema description coverage, no output schema, and no annotations compensating for result behavior, the description is far too thin. It omits what is perturbed, how results are reported, and how the rollback behaves, leaving the agent unable to use the tool correctly.

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% for both parameters. The description references '±ε', giving a faint gloss on the epsilon parameter, but says nothing about max_params (the cap on how many parameters are perturbed) or default/range semantics. With low coverage the description should compensate but does not.

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 ('Шевелит параметры на ±ε и откатывает') describes a mechanical action — perturbing parameters by ±ε and reverting — but never states that this is a design audit, a sensitivity/sensitivity-analysis operation, or what the tool actually produces. An agent cannot distinguish it from a generic param-jiggle helper among siblings like params_set or measure without opening the schema.

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?

There is no indication of when to use this tool versus siblings such as params_set, validate, or measure. No prerequisites, no exclusions, no alternative routing are provided. The agent must guess the use case entirely.

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