Ask question

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

Annotations already indicate readOnlyHint=true, openWorldHint=false, and destructiveHint=false. The description adds behavioral context: it doesn't invent facts outside the instructions and explicitly says to state when instructions are empty/insufficient. This goes beyond the annotations and helps the agent calibrate expectations. It doesn't discuss rate limits or other behavior, but given the read-only nature and simple purpose, the description covers the critical aspects.

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, with the primary instruction front-loaded and the constraint/instruction-following behavior right after. Every sentence earns its place; no filler words or redundant phrases.

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 single-parameter read-only tool with 100% schema coverage and no output schema, the description is largely complete. It covers when to use, constraints, and edge behavior. It could arguably mention what a 'good answer' looks like or how to handle partial instructions, but given the simplicity and annotations, the missing piece is minimal.

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%: the property 'question' has a description in the schema ('The user question to answer per operator instructions'). The tool description essentially restates this, so it doesn't add much semantics beyond the schema. A baseline of 3 is appropriate because the schema already documents the parameter fully.

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 states the verb ('answer') and the resource ('the operator's current instructions'), which differentiates it from the sibling tools: get_instructions and set_instructions manage the instructions, while ask_question uses them to answer. It also conveys the tool's scope and constraints. However, it doesn't explicitly name the sibling tools or contrast with them directly, so it stops just short of a 5.

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 says 'Use when the user asks something that should be answered per the operator's current instructions.' This provides clear conditions for when to use the tool. It also includes guidance on what to do when instructions are empty or insufficient, which helps in edge cases. It doesn't explicitly exclude using it for non-question situations or name alternatives, but the context makes the decision fairly clear.

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