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

Annotations already cover safety and idempotency (readOnly, idempotent, non-destructive), so the bar is lower, and the description still adds key context the annotations cannot: the response is a sample/fixture rather than real briefs, it costs nothing, and it requires no wallet. It stops short of describing sample completeness or how the preview differs in coverage from the paid payload.

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?

Four short sentences, front-loaded with the [FREE] tag and the sample-response framing before routing advice. Every sentence carries distinct information (cost, when to buy, when to skip with alternatives, invocation cost), with no padding.

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?

With no parameters and no output schema, the description's only obligations are to explain what the preview returns, that it is free, and how it relates to the paid tool and siblings — all covered. Minor gap: it does not indicate whether the preview data is representative in breadth (how many days) or whether paid output has a different format.

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?

Zero parameters, so the baseline is 4. The description reinforces this with 'no arguments needed', which matches the empty schema and prevents an agent from trying to invent a date range or day count.

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?

States a specific artifact (a free sample response for signal_history) and the resource it previews (multi-day archive of Daily Agent Signal). It explicitly names the sibling it is NOT (signal_history) and the preview relationship, so an agent can distinguish it from the paid tool and from the other signal_* variants.

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?

Gives explicit when-to-use for the paid sibling ('Buy signal_history when you want the full briefs for several recent days') and when to skip it, with three named alternatives for the closest edge cases (signal_latest for most recent, signal_day for one date, signal_continuity for thread persistence). Nothing is left to inference.

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