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

Goes well beyond the annotations: discloses the USD 0.01 charge and that it only happens after explicit authorization, that up to five excerpts are sent to an AI service, that no-match returns 'unsupported' with no charge, that identical question plus source versions reuse the saved purchase, and that removed/replaced sources yield 'stale' without leaking the old answer. This fully justifies readOnlyHint=false and idempotentHint=false.

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?

Purpose is front-loaded and every sentence carries distinct information about cost, failure modes, or citations. The telegraphic phrasing of lines like 'No retrieval match returns unsupported without a charge' and 'Removed or replaced sources produce stale' slightly impedes first-pass readability.

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 paid, stateful generation tool with no output schema, the description covers cost gating, billing reuse, no-match and stale-source outcomes, and the exact citation fields (document ID, version, content hash, excerpt). An agent has everything needed to call it safely and interpret results.

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%, so base_id, question, authorize, and price_usd are already documented. The description reinforces the authorization and pricing semantics ('costs USD 0.01 after explicit authorization') but adds no format or edge-case detail not already in the schema.

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 ('Ask a question with sources from your base') and constrains scope to one base owned by the current personal account. It also distinguishes itself from the sibling get_base by noting get_base returns the latest answer, so an agent can separate asking from reading.

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 clear prerequisites for invocation: explicit authorization, price_usd copied from get_base, and one personal-account base. It signals retrieval-only alternatives indirectly via 'No web search, tools or external actions' and 'get_base also returns the latest answer', but it never explicitly says when to prefer search_base or get_base_answer over this paid call.

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