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

Annotations already provide idempotentHint=true, readOnlyHint=false, and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context beyond annotations: it requires an agent API key via Bearer or X-API-Key, is not guest-callable, and attaches a buyer-funded escrow to the session. It doesn't explain side effects when both identifiers are supplied, but there is no contradiction with the annotations.

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 compact and front-loaded: purpose, prerequisites, authentication, parameter preference, and REST endpoint are each covered in just three sentences. No filler is present, and the small overlap between 'Requires an agent API key' and 'Not guest-callable' does not hurt clarity.

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 3-parameter tool with no output schema, the description provides the key invocation context: an already-opened session, auth requirements, the escrow attachment mechanism, and the REST route. It does not describe the return value or explicitly explain how a proof escrow is created, but those are inferable from the workflow and sibling tools. It is complete enough for a competent agent to call it correctly.

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?

The input schema describes only session_id; open_tx_hash and proof_escrow_id are mostly bare fields. The description compensates by marking open_tx_hash as preferred over proof_escrow_id and linking both to a buyer-funded proof escrow, which helps an agent choose between them. The exact meaning of a transaction hash versus an escrow ID is still left partially implicit, though the field names and schema titles help.

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 pins down a specific action: attaching a buyer-funded proof escrow to an opened data session to buy per-query access. It names the exact fields involved (open_tx_hash, proof_escrow_id) and sets it apart from data_preview, which is called out as the free first taste. The verb-resource pair is unambiguous and distinct from the sibling tools.

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 clearly says when to use this tool: after opening a data session, when you want paid per-query access, and with agent API-key authentication. It also gives an exclusion ('Not guest-callable') and directs new users to data_preview for a free trial. It does not explicitly contrast with data_session_fund, but the escrow-specific workflow is sufficiently contextualized.

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