step

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

Annotations already declare the mutation/safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), lowering the bar. The description adds the semantics of each step mode, which is genuine behavioral content, but does not state prerequisites (an active session must exist) or what happens on failure. Adequate but not rich.

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?

A single sentence, front-loaded with the verb, packing all four mode definitions without waste. Every clause earns its place.

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 step tool with full schema coverage, complete annotations, and no output schema, the description covers the mode space well. Minor gaps remain around session prerequisites and post-step state, but nothing critical for correct invocation is missing.

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 100%, so baseline is 3, but the description adds real value the schema lacks: it documents each enum value of kind ('over', 'into', 'out', 'instruction') and explains the interaction of over=true with kind='instruction', which the schema's terse per-field descriptions do not cover.

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 ('Single-steps the target') and enumerates all four step kinds with their semantics. An agent immediately understands the operation. It does not name sibling alternatives like run_to_line, continue_execution, or debug_until, so it misses the top-tier sibling 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 per-mode glosses ('into calls', 'run until the function returns') imply when each kind is appropriate, which gives usable context. But there is no explicit when-to-use-this vs alternatives guidance, e.g. versus run_to_line or debug_until. Usage is inferable rather than declared.

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