deep_research

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

Annotations all false, so description bears the burden. Description explains multi-step process (query decomposition, parallel retrieval, gap analysis, synthesis) and checkpointing behavior. While it doesn't explicitly state read/write nature, the checkpointing implies statefulness, and the overall process is well-described.

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 concise, front-loading the purpose, then differentiation, usage guidance, prerequisite, and example. Every sentence adds value 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 complexity, the description covers key aspects: purpose, differentiation, prerequisites, and checkpointing. However, it does not describe the output format or return value, which could aid agent understanding. Nonetheless, for a research tool, the output is somewhat implied.

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%, so parameters are already well-documented. The description adds a usage example that demonstrates the required parameters but does not add new semantic details for optional parameters like max_chunks or preset beyond what schema provides. Baseline 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 tool performs deep research on codebase questions using multi-step reasoning, distinguishing it from ask_question (single retrieval). It specifies the resource (codebase) and the action (deep research), making the purpose unambiguous.

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?

Explicitly says when to use (complex architectural questions) and when not to (simple queries better suited for ask_question). States prerequisite (index_repository must be called first) and mentions checkpointing for long-running tasks, with reference to list_research_checkpoints for resumption.

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