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

Annotations only declare readOnlyHint and openWorldHint=false; the description adds the non-obvious behavioral trait an agent actually needs — a staleness floor of at least one hour — plus the output scale (0-100). It doesn't state caching/refresh behavior or rate limits, but the latency disclosure is the material one here.

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?

Three short clauses, with the 'FREE' qualifier and the latency caveat front-loaded before the upsell pointer. Every fragment carries information; nothing is repeated or 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 output schema, the description carries the burden of describing the return, and it does: a categorical label plus a numeric score, explicitly delayed. Adequate for a no-arg teaser, though it could say whether the label set is fixed or what the score means directionally.

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 there is nothing for the description to clarify and the baseline of 4 applies. The mention of the 0-100 range describes the return value rather than an input, which is still useful signal.

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?

Names the specific resource and output ('risk-on / risk-off regime label and 0-100 score'), plus the key qualifier 'delayed at least 1 hour'. It also distinguishes itself from the sibling regime_now by stating what that tool adds, so an agent can separate the two without opening either schema.

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 clear selection logic: take this free delayed teaser, or pay $0.02 for regime_now when the live score, reasons, drivers and components are needed. It does not mention the other closely-named sibling regime_full, leaving one routing decision implicit.

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