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

Annotations already declare a safe read-only, idempotent, open-world operation, so the bar is lower — yet the description still adds real value: it requires a personal key, warns results count against a daily allowance, and discloses that candidates are retrieved by meaning so differently-worded answers can be missed. These are exactly the operational and reliability facts an agent cannot infer from annotations.

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 carrying distinct load: capability+output, invocation trigger, retrieval caveat, and resource requirements. Capability is front-loaded and there is no 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 an output schema present, the return shape needn't be restated, and annotations cover the safety profile. The description fills the remaining gaps — auth, rate allowance, and retrieval reliability — so an agent has everything needed to call it correctly.

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 the 'question' (yes-or-no, 15-600 chars) and 'field' (arxiv category, empty = all fields) parameters are already fully documented. The description adds only marginal framing about the question's scope, so the 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 and resource ('read the papers closest to a question'), defines the field-wide scope, and specifies the per-paper output (yes/no/not-addressed with the deciding sentence quoted). It is clearly distinguishable from single-claim siblings like check_claim by the 'across a field' framing, though it never names an alternative tool explicitly, which keeps it out of 5 territory.

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?

'Call when a user asks whether something holds across the literature' gives a clear usage trigger, and the semantic-matching caveat tells the agent when results may be incomplete. It stops short of the explicit when-not/named-alternative guidance that would earn a 5.

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