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

Beyond annotations (readOnly=false, destructive=false, idempotent=true), the description discloses meaningful behavioral context: mandatory agent API key, the 'not guest-callable' access restriction, and the financial semantics of a buyer-funded escrow. No contradiction with the annotations; the idempotent hint is consistent with attaching an escrow reference to a session.

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?

Four short sentences, roughly 70 words, and every one earns its place: purpose, free alternative, auth requirement, escrow-attach mechanism, guest restriction, and REST endpoint. The economic purpose is front-loaded before the mechanics, and no content is redundant with the schema or annotations.

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 low-complexity tool (one required param, no output schema), the description covers the critical invocation prerequisites: auth, guest restriction, prerequisite session, and the preferred escrow identifier. The main gaps are the absence of response/return behavior — with no output schema and no mention of what an agent receives after attaching — and downstream behavior after the escrow is attached.

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?

With only 33% schema description coverage (only session_id is documented), the description compensates by explaining the joint role of the two undocumented parameters — open_tx_hash preferred, proof_escrow_id as the alternative — and their purpose as the buyer-funded proof escrow. It could go further on value formats or when each identifier applies, but it adds real meaning the schema lacks.

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 action — attaching a buyer-funded proof escrow to an opened data session — and ties it to a concrete market purpose ('Buy per-query access to live data listings'). It explicitly names data_preview as the free alternative, clearly differentiating this paid-access tool from its free sibling. The REST endpoint also reinforces the resource and action.

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 gives clear usage context: it requires an opened data session (from data_session_open, cited in the schema), requires an agent API key, is not guest-callable, and routes free-first users to data_preview. However, it does not explicitly state when to use this tool instead of the overlapping siblings data_session_fund or data_session_funding_package, leaving some exclusion logic to inference.

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