Search arXiv

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds a genuine behavioral trait beyond that: the no-query default behavior and the default category (cs.AI), which an agent needs to predict results. It still omits pagination and return-format details, keeping it below 5.

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?

Two tight sentences, front-loaded with the core purpose followed by the no-query behavior and category reference. Every clause carries information; nothing is 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?

For a read-only search tool with no output schema, the description covers purpose, default behavior, and the category domain an agent needs to call it correctly. The unexplained 'sort' enum is a minor residual gap, not a blocker.

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 only 60%, so the description must carry weight, and it does: it supplies the concrete category vocabulary (cs.AI, cs.LG, cs.CL/NLP, cs.CV, cs.RO, cs.SE, stat.ML) and the default category, which the schema only gestures at with an example. It does not explain the 'sort' enum or 'limit' bounds, so it doesn't fully compensate for the gap.

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 ('Search arXiv papers'), so the agent immediately knows this retrieves academic preprints rather than news (hackernews_*) or repos (github_trending). Sibling differentiation is implicit via the resource domain rather than by naming an alternative, which keeps it 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?

The description does describe one important usage mode: with no query it returns the latest submissions, defaulting to cs.AI. However, it gives no guidance on when to pick this over the sibling tools (tech_trends_digest, hackernews_search) or on which sort mode to choose, leaving usage largely implied.

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