research_web_followup

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

Annotations provide readOnlyHint=false and openWorldHint=true, but the description adds that the tool is synchronous and fast with no background work. No destructive behavior is mentioned, but the description does not contradict 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?

The description is two sentences, front-loaded with the main purpose, and contains no extraneous information. Every sentence adds value: first defines the action, second explains context and performance.

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 covers purpose, context (interaction_id), and behavior (synchronous). It does not explain return format, but an output schema exists. The prerequisite of a completed deep research is implied by 'completed report' and schema description.

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 100% with clear parameter descriptions. The description reinforces that interaction_id maintains context but adds no new semantic detail beyond what the schema already provides. The baseline score 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 the action ('Ask a follow-up question') and the resource ('completed Deep Research report'). It distinguishes from sibling tools like research_web and research_web_status by specifying it's a follow-up, but does not explicitly contrast with research_deep or other follow-up-like 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 explains that it uses previous_interaction_id to maintain context, implying it should be used after a completed deep research. It notes it's synchronous and fast, guiding the agent to expect quick responses. However, it does not state when not to use it or provide alternatives.

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