perform_research

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

With no annotations, the description carries full burden. It discloses the cascading behavior but lacks details on side effects, error handling, or output format. The cascade order adds value, but transparency is limited.

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 a single sentence that is front-loaded with the action and key concept. It contains no filler and conveys the essential information efficiently.

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 tool has 5 parameters and no output schema. The description covers the main cascade process but omits the output format (e.g., whether it returns a report or answer) and how parameters like 'performWebSearch' integrate. This leaves gaps for the agent, though the schema covers parameter details.

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 baseline 3. The description does not reference any parameters or add meaning beyond the schema. For example, it does not explain how 'confidenceThreshold' relates to the fallback behavior mentioned in the description.

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 verb 'perform research' and specifies the resource as cascading sources (project files → knowledge graph → environment resources → web search fallback). This distinctively differentiates it from sibling tools like llm_web_search or search_codebase, which focus on single sources.

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 implies when to use by detailing the cascading order (local sources first, web as fallback), providing clear context. However, it does not explicitly state when not to use this tool or mention alternative tools for specific scenarios.

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