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

Annotations declare openWorldHint=true, readOnlyHint=false, idempotentHint=false, destructiveHint=false, so the agent already knows this is a non-read-only, non-idempotent, open-world call. The description adds genuinely new context not in the structured fields: a hard cost of 0.50 USD via MPP, the deterministic nature of the package, and preservation of per-item verdict/evidence-quality semantics. It stops short of explaining payment mechanics, failure/refund behavior, or per-item error handling.

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 cost and capability, which is good, but the usage clause is duplicated: 'rather than one question, claim, timeline, or evidence request' is immediately followed by the redundant 'Use for multiple distinct research items.' One of those sentences should be cut.

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?

An output schema exists, so return-value explanation is unnecessary, and the description covers cost, scope, batch limits, and selection criteria. What remains thin is operational detail for a paid, non-idempotent tool — e.g., what happens if some items fail or whether the fee applies per call or per item.

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 100% and there is a single parameter, so the schema already documents the items array, its string-or-object union, the 1-20 bounds, and the item type enum. The description's 'up to 20 distinct' and 'per-item verdict and evidence-quality semantics' add only marginal framing beyond that, which matches the baseline 3 when the schema does the heavy lifting.

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 (process) and resource (up to 20 Bitcoin claims, questions, or evidence requests) bundled into one deterministic research package, and explicitly frames the unit of work as 'multiple distinct research items' rather than a single one. This lets an agent separate it from answer_bitcoin_question, verify_bitcoin_claim, build_bitcoin_timeline, and get_bitcoin_evidence_pack without opening any schema.

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 an explicit positive condition ('multiple distinct research items in one invocation') and an explicit exclusion ('Do not wrap a single item merely to use the batch product'), and names the single-item alternatives it replaces. The selection rule is fully determined.

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