Reflect: Add Prompt Step

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

Beyond the annotations (readOnlyHint=false, etc.), the description discloses that the prompt can only be literal text, cannot contain dynamic syntax or secrets, and can perform browser navigation and tab/enter in Web recordings. It also implies the session must be active. These are behavioral constraints not visible in 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?

Purpose is front-loaded and the toolset label helps orientation. However, the 'Parameters' section duplicates the input schema descriptions almost exactly, creating redundancy. The structure is organized but not optimally concise for an agent that already has schema access.

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 tool has only two required parameters, both fully documented, and the description adds prompt constraints and web-recording behavior. It does not explicitly state the prerequisite of an open session from reflect_connect_to_session or describe success/error responses, but for a simple append-step mutation tool, the coverage is adequate.

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%: both sessionId and prompt are described in the input schema, and the description's 'Parameters' block repeats those descriptions nearly verbatim without adding new meaning. Examples like 'Click on the back button' are already present in the schema description, so the description adds no semantic value beyond the schema.

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 opens with 'Add a natural language prompt step to an active Reflect recording session' – a specific verb ('Add'), a precise resource ('prompt step'), and a target context ('active ... recording session'). This clearly differentiates it from sibling tools like reflect_add_segment or reflect_delete_previous_step without needing to inspect schemas.

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 implies the tool is for adding prompt steps during an active recording session and gives constraints on prompt content (literal text only, no template variables/secrets) and capabilities in Web recordings. However, it does not explicitly state when to prefer this over alternatives like reflect_add_segment, nor provide exclusions or prerequisites other than 'active'.

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