Reflect: Add Prompt Step

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

Annotations indicate non-read, non-destructive, non-idempotent behavior. The description adds that the tool adds a step to an active session, and specifies that prompts cannot contain dynamic syntax. It also notes browser navigation capabilities for Web recordings. This provides useful behavioral context beyond annotations, though it doesn't detail side effects like whether the session is saved.

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 well-structured with a clear purpose statement, toolset label, and parameter list. It is front-loaded and each section serves a purpose. Slightly verbose for the parameter detail that mirrors the schema, but overall efficient.

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 explains input parameters and constraints well, but lacks any mention of return values or output. Since there is no output schema, the agent has no information about what the tool returns (e.g., success indicator, step ID). This is a notable gap for a tool that writes data.

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 description adds marginal value. However, it clarifies the prompt's limitations (no template variables, literal text only) and the sessionId's role, which are not fully captured in the schema. The description enriches the parameter meaning without being redundant.

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 action ('Add') and the resource ('a natural language prompt step to an active Reflect recording session'). This verb+resource combo is specific and distinguishes from sibling tools like 'reflect_add_segment' or 'reflect_delete_previous_step'. No ambiguity.

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 description provides clear constraints for using the prompt (single action, no template variables) and context-specific capabilities for Web recordings. However, it does not explicitly mention when to use this tool versus other reflect tools, such as when to add a step vs. run a test. The guidance is adequate but lacks explicit exclusions or alternatives.

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