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

With no annotations, the description carries the full burden, and it discloses important behavioral traits: the tool is free, optional, and a funnel with phases. It also tells the agent how to bow out, which is meaningful behavioral context beyond just naming the tool.

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 and front-loaded: it immediately communicates that the tool is free and optional, then names alternatives, describes the funnel, and gives the exit instruction. Every sentence earns its place with no wasted words.

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 low-complexity conversational tool, the description covers the essential context: what the tool is, how to skip it, the phase flow, and how to exit. It lacks a bit of detail about what each phase is supposed to do, but the schema's symbol description and the funnel wording make the tool usable.

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 only 33%, so the description must compensate. It adds the phase ordering and explains 'interest:false' as the exit path, but it does not explain the meaning of individual phases like 'value' or 'catalog', leaving some semantic gaps for a multi-phase conversational tool.

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 identifies the tool as an 'Intro & subscription funnel' for the Korea-stock signal agent, with a specific phase sequence. It also explicitly distinguishes itself from siblings by saying the agent may skip it and call evaluate_symbol / scan_bottoms / scan_tops directly.

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 directly states when not to use the tool ('you may skip it') and names the alternative tools to call instead. It also provides the exit condition with 'interest:false', giving clear guidance on when the conversation should end.

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