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

Annotations cover the safety profile (readOnlyHint=true, openWorldHint=false), and the description adds the critical non-schema facts: this is a paid call at $0.02 USDC and delivers a snapshot of the current regime plus 'what changed since yesterday'. That cost and temporal-scope disclosure is real value beyond the annotations. It does not mention latency, caching, or rate limits, which keeps it from a 5.

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 purpose question and the price are front-loaded, and the long output enumeration earns its space because there is no output schema to carry that information. The component list is dense but readable; a tighter version could group the nine components rather than name each, but it is not padded.

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 zero-required-parameter snapshot tool with no output schema, the description does the heavy lifting by enumerating every returned field including the nine component scores and the day-over-day delta. It leaves the meaning of the 0-100 scale and the specific regime labels undefined, which is the only real gap.

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 coverage is 100% and the single api_key parameter is fully documented there, so the baseline is 3. The description's 'No parameters' is slightly at odds with the presence of an optional api_key, though it correctly conveys that no query inputs are needed for the call. It adds nothing beyond the schema, so it sits at the baseline.

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?

Opens with a specific question the tool answers ('Is the market risk-on or risk-off right now, and why') and then enumerates the exact payload: 0-100 composite score, regime label, confidence, sub-scores, drivers. An agent knows precisely what this returns. It stops short of a 5 because it never distinguishes itself from the sibling regime_full or free_regime tools, which an agent must otherwise guess between.

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 states the price and that there are no parameters, which implies a point-in-time snapshot, but gives no explicit when/when-not guidance. With siblings named free_regime and regime_full present, the absence of any routing ('use this for the current read, regime_full for history') leaves the agent to infer the paid-vs-free and now-vs-full trade-off entirely on its own.

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