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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, so the write and non-idempotent nature is covered structurally. The description adds genuinely new context the annotations lack: per-query pricing (0.01 USDC), a session cap (max 20 queries), and the prepaid model. It does not explain what a session open returns, whether an existing session is reused, or what happens on a repeat call, which matters for a non-idempotent paid mutation.

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 action-and-flow sentences are front-loaded and efficient. However, the embedded concrete listing name, slug, pricing string, and doubled parentheses are noise that does not generalize and consumes attention without helping an agent select or invoke the tool.

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 carries the burden of saying what an agent gets back from opening a session (session handle, expiry, cost) and does not. Payment and funding sequencing are only gestured at with "then fund and query." Adequate to start a call, but incomplete for a six-parameter paid mutation with zero required fields.

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?

Schema description coverage is only 50%: listing_id, listing_slug, and buyer_address are documented in the schema, but max_queries, open_tx_hash, and proof_escrow_id are not. The description hints at a query cap ("max 20 queries/session") but never explains max_queries, open_tx_hash, or proof_escrow_id, so it does not compensate for the coverage gap on the more opaque parameters.

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 verb and resource: "Open a prepaid session" for per-query access to live data listings, and it names data_preview as the free alternative. It is distinguishable from siblings like data_session_fund or data_session_query. The embedded hardcoded listing line ("Listing: msrwatch: Microsoft Research Blog...") blurs whether the tool is generic or listing-specific.

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?

"first taste free via data_preview" gives one clear alternative, and "Open a prepaid session, then fund and query" implies the ordering with data_session_fund and data_session_query. There is no explicit when-not guidance, no statement about what happens if a session already exists, and the hardcoded listing line reads as if the tool targets one specific listing, which could mislead an agent.

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