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

Beyond the annotations, the description adds genuinely useful behavior: per-query pricing (0.01 USDC), the existence of a free preview path, and the fact that the tool returns funding instructions rather than executing payment. That last point also resolves the apparent tension between "Buy" and readOnlyHint=true. It still omits what the returned fund instructions contain, whether they expire, and how settlement is confirmed.

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 compact sentences with no filler, and the core action is front-loaded. However, the embedded listing name and price read as data specific to one listing rather than durable tool semantics, and the sentence order (purpose → free alternative → response) buries the critical "returns fund instructions" detail in an appended clause.

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 is the only source describing what comes back, and it does name the return value (fund instructions) — but not its structure or the follow-up call needed to complete payment. For a financially consequential step in a multi-tool flow (open → fund → query), the description should at least indicate the sequence after funding instructions are received.

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?

There is a single session_id parameter with 100% schema description coverage, and the schema already explains that the UUID comes from data_session_open; the description's "after data_session_open" merely echoes that. No additional meaning (validation, failure modes for invalid or expired sessions) is added, so the schema is doing all the work.

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 opens with a clear verb+resource ("Buy per-query access to live data listings"), but the closing sentence ("Returns fund instructions after data_session_open") describes a different outcome than "buying," leaving the agent unsure whether this tool purchases access or merely produces payment instructions. The hardcoded single-listing detail (msrwatch / 0.01 USDC) muddies whether this is a general-purpose tool or a listing-specific one, and the name/title ("funding_package") is not clearly reconciled with either framing.

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 does point to a free alternative (data_preview, "first taste free") and states a prerequisite (data_session_open must come first), which is real guidance. However, it never says when to use this versus the very similarly named data_session_fund, data_session_attach_escrow, or data_session_query siblings, and gives no when-not conditions or ordering rules beyond the one prerequisite.

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