Research Deep

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

Annotations only cover readOnlyHint and openWorldHint; the description goes further by disclosing a consequential behavioral trait: CONFIRMED and STRONG INDICATOR proposals degrade to UNKNOWN because this route neither retrieves nor verifies. That materially warns the agent about output reliability, which the annotations 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?

Two short, front-loaded sentences plus a phase list, with zero filler. The most important constraint (no retrieval, tier degradation) is stated up front.

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 and annotations covering the safety profile, the description only needs to convey routing and behavioral caveats, which it does via the phase list and the UNKNOWN-degradation warning. Adequate, though it could be stronger with an explicit sibling comparison.

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 topic, scope, and thinking_level are already fully documented in the schema, including enums and defaults. The description adds no parameter-level detail beyond what the schema provides, 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+resource ('Run three-phase model-only synthesis') and enumerates the phases, making the operation concrete. The qualifier 'without external source retrieval' implicitly separates it from retrieval-based siblings like research_web or research_execute, though no sibling is named outright.

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 phrase 'model-only synthesis without external source retrieval' implies when this route is appropriate versus the retrieval-oriented research siblings, but there is no explicit when-to-use/when-not statement or named alternative. Usage is inferred rather than stated.

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