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

Annotations already indicate this is not read-only (readOnlyHint=false) and not destructive, but they don't convey that each query consumes prepaid credits. The description adds the per-query cost and a max of 20 queries per session, which is useful. However, it does not explain side effects like balance decrement, error handling for insufficient funds, or receipt mechanics, leaving the agent with partial transparency.

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 compact at three sentences, but the first two focus on marketing and a specific listing rather than invocation essentials. The crucial sequence is in the final sentence, which is useful but not front-loaded. There is no redundant fluff, but the structure could prioritize actionable info better.

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 tool with five parameters and no output schema, the description provides only the workflow sequence and a usage limit. It does not specify query format, response contents, receipt behavior, or error conditions. The schema fills a little, but the description leaves too much to inference for reliable 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 low (40%: only session_id and sandbox_receipt have descriptions; query, k, and delivery_receipt are undocumented). The description does not elaborate on any parameter, so the agent gets no additional meaning for 'query', 'k', or 'delivery_receipt'. With low coverage, the description should compensate but does not, leaving parameter semantics poorly supported.

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 clearly positions this tool as the query step in the data-session workflow, referencing the sequence data_session_open → data_session_fund → data_session_query and contrasting with the free data_preview. The phrase 'Buy per-query access' is slightly misleading (the action is running a query, not purchasing), but the schema's own description 'Run a prepaid query against a funded data session' resolves that ambiguity. It distinguishes from siblings by naming the workflow position and the free alternative.

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 gives the usage sequence and points to data_preview for a free first taste, telling an agent when to use this tool (after opening and funding a session) and when to use a sibling (for trial). It does not list explicit exclusions or conditions beyond the sequence, but the context is clear enough for an agent to choose correctly.

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