ask_papers

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

Adds substantial context beyond the annotations: each call is a paid LLM request, it is rate-limited, answers are grounded exclusively in indexed content, the tool refuses when knowledge is absent, and returned passages must be treated as data not instructions. This covers cost, limits, and prompt-injection safety that the readOnly/openWorld hints do not convey.

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?

Four sentences, each earning its place: purpose first, then routing to the alternative, then grounding behavior, then a safety caveat. Front-loaded and free of filler.

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 annotations and an output schema already present, this description still supplies the cost, rate-limit, grounding, and safety nuances an agent needs. Nothing material for correct invocation is missing.

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 coverage is 100% and the single 'question' parameter is fully documented (1-500 chars), so the schema carries the load. The description frames the question as domain-scoped but adds no syntax or length guidance beyond what the schema states, so baseline 3 applies.

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 ('ask a question') and resource ('Raman spectroscopy of carbon nanotubes' papers) and clarifies the answer is generated only from indexed papers with supporting passages. It distinguishes itself from search_papers by describing the synthesized-answer-plus-passages output.

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?

Explicitly names the alternative: 'prefer search_papers when passages are enough,' giving a concrete selection condition. It also sets a behavioral boundary — if the papers lack the answer, say so rather than fabricating — which tells the agent when not to rely on general knowledge.

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