Step

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

With no annotations provided, the description carries the full behavioral burden and does an excellent job: it discloses that actual model-time growth is verified, explains that ProjectStep can falsely report success, and states that the tool now refuses when time does not move. This is genuine transparency beyond what the schema or annotations provide.

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 compact, front-loads the core action, and then adds the important behavioral caveat. The historical note about previous behavior is slightly extra but earns its place by clarifying the current failure semantics.

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?

The description is complete enough for a single-parameter tool with an output schema: it explains what the tool does, how success is verified, and when it will refuse. It could be more complete by giving explicit guidance about when to choose step over run, but that is a minor gap.

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 100%, so the parameter is already documented with its default and constraints. The tool description adds little beyond the word 'specified number', so it does not meaningfully improve on the schema. Baseline 3 is appropriate.

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 clearly states the tool executes a specified number of calculation steps ('Выполнить указанное число шагов расчёта'), naming both a concrete verb and resource. It does not explicitly distinguish itself from sibling tools like run or get_time, so it misses the last step of differentiation.

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 behavioral note implies when the tool is unreliable (projects without a calculation layer or with unconnected block inputs), but it does not explicitly say when to use this tool instead of alternatives like run or set_calc_time. The usage context is mostly inferred from the core action rather than stated.

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