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

With no annotations, the description carries the full burden and does so: it discloses suspension status, the frozen source, the exact oracle response shape (200 with status suspended), that no charge occurs, the auto-resume condition, and the per-call price ($0.015 USDC). That is unusually rich disclosure of state, cost, and failure behavior.

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 most urgent fact (SUSPENDED, does not charge, prefer these live tools) is front-loaded, which is correct for an agent deciding whether to call at all. It is longer than ideal with several paragraphs, but each block (status, simulation behavior, pricing, sibling contrast) contributes distinct information.

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?

No annotations and no output schema, yet the description explains the return payload (5th-95th percentiles, model parameters, confidence intervals, optional MC paths), the cost, the required input, and current operational state. An agent has everything needed to decide and to call correctly, with only 'simulations' left implicit.

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 0%, so the description must compensate, and it mostly does: days range 30..365 with default 90, model options 'gbm'/'merton' with default 'conformal', and current_price required. The only omission is the 'simulations' parameter (default 20000), which is undocumented in both places.

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 verb+resource ('SIMULATE a card's price path over a horizon') and names exactly what the output contains (percentiles, model parameters, CIs, Monte Carlo paths). It also explicitly distinguishes itself from card_forecast, so an agent can route 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 explicit when-to-use ('only when the user wants a different horizon, the full percentile curve, or a Monte Carlo model') and when-not (card_forecast is the free fixed 30-day read). It further names live alternatives (loan_terms_preview, sports_board, the free /jp/card page) and even the exact trigger phrase '6 months out?'.

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