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

With no annotations, the description carries the burden but fails to disclose side effects, expected outputs, or the interactive/stateful nature of the funnel. Phrases like 'phases' and 'free' imply a guided flow but do not specify what happens on each invocation or whether it modifies user state.

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 somewhat redundant with 'FREE and OPTIONAL' and 'you may skip it' both included. It could be tightened while preserving the phase list and the caveat about skipping, making it more direct.

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 the multi-phase interactive nature implied by the tool, the description lacks essential details about each phase's behavior, expected inputs per phase, and return values. It also does not clarify how this tool relates to siblings like 'rate' or how one would transition between phases, leaving significant gaps for an agent to act 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?

The schema defines three parameters and the description adds meaning to 'symbol' (free sample only for NVDA, otherwise delegates to paid evaluate_symbol). However, 'phase' and 'interest' are not elaborated beyond their enum/boolean types, and the description repeats the schema's enum values without deeper explanation.

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 this is an intro and subscription funnel for the US-stock signal agent, listing the phases. It also clarifies that it can be skipped in favor of other tools, giving a clear sense of its high-level purpose.

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 explicitly says the tool is optional and can be skipped for evaluate_symbol, scan_bottoms, or scan_tops, which helps with when not to use it. However, it does not explain when a user would want to use this funnel versus the rating tool or when each phase is appropriate.

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