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

Annotations already declare readOnlyHint=false and idempotentHint=true, so the mutation and idempotent nature are covered. The description adds useful context beyond annotations: authentication requirement (Bearer or X-API-Key), guest-call restriction, and the REST endpoint. It does not explain what happens after attaching escrow (e.g., whether funds are committed or how per-query billing triggers), which is a meaningful gap for a financial transaction.

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 a reasonable length (~55 words) and every sentence carries some information, including the helpful REST path. However, it is not well front-loaded: the opening sentence is promotional ('first taste free') rather than functional, delaying the core attach-escrow purpose to the third sentence. The auth and guest-call details are placed before the primary action.

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 mutation tool with no output schema, the description provides the essentials for a correct call: auth mechanism, endpoint template, session_id source (referenced in schema), and the escrow reference options. Missing are return/response expectations and post-conditions (what a successful attach enables, whether the escrow is partially consumed). An agent could invoke it but would be uncertain about the outcome it commits to.

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, the burden falls on the description. It adds real value by stating that open_tx_hash is preferred over proof_escrow_id and that either serves as the escrow reference. However, it does not explain where these identifiers come from or how the preference decision should be made, and the schema itself leaves open_tx_hash and proof_escrow_id semantically empty.

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: attach a buyer-funded proof escrow to an opened data session. It clearly identifies the resource (data session escrow) and distinguishes itself from data_preview by framing this as the paid per-query path. The opening 'Buy per-query access' phrasing is slightly indirect, but the core verb+resource is unambiguous by the third sentence.

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 conveys when this tool fits: it's the paid path contrasted with data_preview's free taste, and it states prerequisites (agent API key, not guest-callable). However, it gives no guidance on how this relates to sibling tools data_session_fund or data_session_funding_package, leaving an agent unsure whether those are alternatives, prerequisites, or complementary steps.

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