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

With no annotations, the description carries the full burden and does: it discloses the suspension state, that the oracle returns 200 with status=suspended, that it does not charge, the resume condition, and the $0.025 USDC per-call cost. It also pro-actively warns that band/VaR percentages are regime-level constants (not a per-card fit) and that sales volume/view counts are absent from the dataset.

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 operational content is useful, but the front-loaded suspension notice and two dated NOTE blocks crowd out the core purpose, which appears only after the temporary status text. Several sentences (the 2026-07-30 correction, the regime-constants caveat) earn their place, but the ordering makes the definition slower to parse than it needs to be.

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 paid, currently-suspended tool with no output schema and no annotations, the description covers cost, status, resume condition, usage routing, substitutes, and dataset caveats, and even points into the response ('see ranked_by'). The remaining gap is parameter semantics, which is addressed elsewhere only weakly.

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 description coverage is 0% for all three parameters, so the description must compensate, and it does so only by naming them: 'Filter by game, limit, and min_price'. There is no guidance on accepted game values, the price currency/units, the maximum limit, or filtering behavior — the schema property names plus defaults are essentially all an agent has.

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?

It names a specific verb and resource — 'a RANKED LIST of individual cards by PRICE VELOCITY (drift), highest absolute movement first' — and explicitly scopes it as 'built for picking cards, not for summarizing the market', which separates it from market_snapshot. An agent can identify the output shape (per-card risk row, bands, VaR, grades) without opening anything else.

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 'Use this when' block gives a concrete trigger ('which cards are moving fastest right now?') and names the alternative for the other case (market_snapshot for whole-market summaries), plus live substitutes loan_terms_preview and sports_board. Both when-to-use and when-not are explicit.

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