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

Annotations are sparse (readOnlyHint=false, idempotentHint=false, destructiveHint=false) and don't disclose side effects. The description does reveal that it's a paid operation (0.01 USDC per query) and caps usage at 20 queries/session, which is useful. However, it doesn't mention that funds will be deducted, that the operation is not idempotent, or what happens on insufficient balance. It adds some behavioral context but not the full burden given no annotation support.

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 two sentences, front-loaded with the core purpose and then the pricing/sequence. It packs essential info (cost, max queries, sequence) without excess verbosity. It earns a 4 for efficiency, though it could be slightly more structured.

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?

This is a 5-parameter tool with no output schema and minimal annotations. The description provides the pricing and sequence but omits critical operational details: what the query string should be, the role of k and delivery_receipt, expected response format, and error conditions (e.g., insufficient funds). For a paid, non-idempotent operation, this is insufficient guidance for correct invocation.

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 40% (only session_id and sandbox_receipt are described in the schema). The main description adds no parameter-level detail: it doesn't explain what 'query' should contain, what 'k' does, or what 'delivery_receipt' is for. The mention of the listing (NASA Image of the Day) is tangential and doesn't clarify parameter usage. Given the low coverage, the description fails to compensate.

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 the action ('Buy per-query access to live data listings') and differentiates it from data_preview (free taste) and the sequence (open/fund/query). It clearly identifies the tool as a paid query step, though it stops short of explicitly saying 'run a query against a session' — that detail lives in the schema description. Overall the purpose is clear and distinguishes from siblings.

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 explicitly provides the usage sequence (data_session_open → data_session_fund → data_session_query) and contrasts with data_preview ('first taste free'), giving an unambiguous when-to-use vs. alternative. It also notes the max queries per session (20), which is a concrete usage constraint. This is exemplary guidance.

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