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

Goes well beyond the annotations (which only say write, open-world, non-idempotent): it discloses the several-minute runtime, the exact five sections produced, that it runs on the user's own account and consumes a quota ('counts against their plan's Ultradeep reviews'), and that it returns immediately with a conversation address plus question_id. Quota consumption and async return semantics are exactly the kind of behavior annotations cannot express.

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-loads the trigger condition and exclusion, then covers output shape, cost, and return semantics in tight declarative sentences. No filler; the five-section list earns its place by setting runtime expectations.

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?

No output schema exists, but the description compensates fully: it explains the immediate return value (conversation address + question_id) and names get_ask_answer as the polling path to retrieve the finished review. Scope, duration, cost, and result retrieval are all covered.

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 both parameters (question, conversation_id) are already documented in the schema, and the description adds no syntax or format detail for either. Baseline 3 applies when the schema carries the parameter burden.

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 — starting a multi-minute, five-section evidence review on a research question — and immediately scopes it against 'a short answer', which distinguishes it from the sibling ask_arn. An agent can tell what it produces without opening the 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 explicit when-to-use ('user asks for a full review of the evidence... beyond a short answer'), when-not ('Not for personal medical advice, doses or symptoms'), and routes follow-up work to get_ask_answer. The trigger condition and the exclusion are both stated, not inferred.

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