Web-search directive (plan only)

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

The description discloses key behavioral traits: mathlas makes NO web call, the agent must perform the search and feed results back via add_finding. Since annotations are absent, the description carries the full burden, and it provides sufficient transparency for agent decision-making.

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 efficient sentences: the first defines the tool's output and behavior, the second gives a usage guideline. Every sentence provides essential information without redundancy.

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?

Given the tool's simplicity (1 parameter, has output schema), the description covers the core purpose, behavior, and usage context. It lists what the plan includes, which helps the agent understand the output, but does not detail the output schema structure.

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?

The parameter 'problem' has 100% schema coverage with a description matching the tool's description. The tool description adds no new meaning beyond the schema for this parameter, so the baseline of 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 clearly states that the tool provides a structured web-search plan, listing specific components like arXiv query strings and sub-fields. It distinguishes itself from sibling tools by explicitly noting that mathlas makes no web call and that the agent must use add_finding to feed results back, which differentiates it from direct search tools.

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 includes a clear usage condition: 'Use when the local index missed.' This tells the agent when to invoke this tool. However, it does not explicitly mention alternative tools or when not to use it, which would make it a 5.

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