navvi_flow

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

No annotations are provided, so the description carries full burden. It discloses behavioral traits: save requires prior navvi_browse prompt, steps/caveats/refs are JSON strings, flows auto-load on domain match, and high/low confidence flows affect execution path. This is comprehensive.

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?

Description is well-organized with clear sections for each action and example calls. It is detailed but not verbose; every sentence adds value. The structure aids readability.

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?

Given 7 parameters, 1 required, and no output schema concerns (has output schema, so return values not needed), the description covers all actions and parameter usage completely. It provides sufficient information for an AI agent to invoke 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%, so description must compensate. It does so by specifying parameter formats (e.g., flow uses 'domain/action-name') and stating that steps, caveats, refs are JSON string arrays. Examples show exact usage, adding significant meaning 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 clearly states that the tool manages flow recipes (reusable browser workflows) and enumerates four distinct actions (list, show, save, delete) with examples. This differentiates it from sibling tools that are single-purpose (e.g., navvi_click, navvi_fill).

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 context for when to use each action, including example calls and parameter format. It mentions that flows are automatically loaded by navvi_browse, but does not explicitly exclude use cases or describe when not to use this tool vs. alternatives. Slightly lacking in exclusion criteria.

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