Deep Research (one round)

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

The annotations already indicate readOnly/openWorld/not destructive, and the description adds meaningful behavioral context: the tool is one round of an iterative workflow, returns gaps with suggested follow-up queries, and should be concatenated into a cited synthesis. This gives the agent useful expectations beyond the annotation flags.

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, front-loaded with the core capability, and contains no filler. The iterative call pattern and final synthesis are stated economically and clearly.

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?

The description captures the essential workflow: perform one research round, follow the suggested follow-ups, stop when gaps are empty, then synthesize with citations. Since an output schema exists, return-value detail is not required. The main gap is the poor explanation of the parameter semantics, but overall the high-level usage context is sufficiently complete.

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 very low (17%), so the description must compensate, but it only vaguely refers to 'suggested_queries' without explicitly mapping it to the 'queries' parameter. The meaning of 'layer', 'recency', 'round', and 'max_sources' is left entirely to the schema, which is insufficient given the low coverage.

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 it performs 'one research round' combining 'complex fused search + coverage analysis + gaps + suggested follow-up queries.' This is a specific multi-phase verb-resource description that also distinguishes the tool from sibling tools like fetch_page and x_search by emphasizing iterative research coverage.

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 gives explicit usage guidance: 'Call repeatedly with suggested_queries until gaps is empty, then synthesize with citations.' This clearly explains the iteration and termination conditions. However, it does not explicitly compare against sibling tools or state when not to use it.

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