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

With no annotations, the description carries the full burden. It discloses the paid nature ($0.01 per call), the payment process (402 challenge, PAYMENT-SIGNATURE header), and the input boundary (no account/no commitment). It leaves the exact output format strangely, but the ranking behavior and payment handling to the agent's required 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 description is longer than necessary, but each sentence earns a place: purpose, universe scope, payment and 402 retry, cold-start benefit, and `pitch` comparison. It is front-loaded with the functional purpose before the payment details, and structured in short, readable chunks.

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?

It is a one-parameter snapshot tool with no output schema, and the description covers the core loop: what it returns, how to rank, how to pay, how to retry on 402, and the difference from contact. It does not specify exact response contents or error cases, and for the paid state, those gaps are minor – reasonable.readable.

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% (the only parameter, limit, is fully specified in the schema with default and max). The description adds no further parameter semantics; it mentions no detail about how limit affects the universe or ordering, which is acceptable because the schema already covers the parameter.

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?

The description states a specific verb and resource: scan an FX snapshot of 48 pairs and return currency pairs at a bottom, ranked most-bottom first. It also distinguishes itself from the sibling tools implicitly (`scan_tops` is the opposite, `pitch` only reports how many). An agent can tell exactly what this tool does without opening schemas.

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?

It explains when to choose it (`Best cold start: you don't need to pick a symbol — this ranks the whole universe`) and points to a free alternative for counting, `pitch`. It does not explicitly say 'use scan_tops for the top picks' but the top/bottom juxtaposition in the tool name plus description is enough for that inference.

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