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

Annotations already declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, so the agent knows this is a non-idempotent mutation. The description adds real value about the payment model (prepaid, per-query pricing, session cap), but says nothing about what opening a session actually creates, whether the tx hash/escrow must be supplied, or what happens on re-open. Given annotation coverage, 3 is appropriate.

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?

Front-loaded with the core action and the free-preview alternative, but the middle is cluttered by a specific listing name and nested parentheses ('(0.01 USDC/query (max 20 queries/session))') that read as leftover example data rather than reusable guidance. Trimmed to the generic pattern it would be tighter.

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 6-parameter, non-idempotent, payment-bearing mutation with no output schema and only 50% param documentation, the description omits the on-chain mechanics (tx hash, escrow id) and the fund/query handoff details. An agent cannot reliably construct a valid call from the description plus schema alone.

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?

Six parameters with only 50% schema description coverage; open_tx_hash, max_queries, and proof_escrow_id are undocumented in both the schema and the description. The text's '(max 20 queries/session)' loosely hints at max_queries but does not explain it, and the on-chain parameters needed to open a session are never mentioned. Description does not compensate for the coverage gap.

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?

States a specific verb and resource: 'Open a prepaid session' for per-query data listings. It also names the downstream siblings implicitly (fund and query) and routes the free-tier case to data_preview, so an agent can distinguish it from the other data_session_* tools. The embedded 'Listing: medicalxpresswatch...' line is a concrete instance rather than a general statement of scope, which slightly muddies the purpose.

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?

Gives a clear sequencing rule: try data_preview first for the free taste, then open a prepaid session, then fund and query. That names the alternative for the preview case and implies when this tool is the right next step. It does not address when to pick this over data_session_funding_package or attach_escrow, so it falls short of full when/when-not guidance.

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