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

Beyond the readOnly/idempotent annotations, the description discloses important behavior: it waits up to 20 seconds for a short answer that is nearly done, returns status if the answer is not ready, and notes that an Ultradeep review takes several minutes. These details materially affect how the agent should invoke and interpret the tool.

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 a single dense sentence with no filler. The usage condition is front-loaded, and the waiting behavior follows immediately, making it easy for an agent to parse.

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?

With no output schema, the description still explains what is returned: the answer with numbered sources once written, or the current status otherwise. It also covers the key timing caveat for short versus Ultradeep answers, which is enough 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 100%, and the schema already explains that question_id comes from ask_arn or start_ultradeep. The description does not add syntax, format, or edge-case guidance beyond what the schema provides, so the baseline 3 is appropriate.

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 a specific verb and resource: reading the answer for a question. It distinguishes itself from ask_arn, start_ultradeep, and list_questions by explaining that it returns the written answer with numbered sources or the current status.

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?

It explicitly says when to use it: when ask_arn or start_ultradeep indicates the answer is still being written, or when the user wants the answer again. This gives the agent clear routing conditions rather than leaving usage implicit.

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