ask_big_brain

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

Without annotations, the description carries the full burden and it delivers: it discloses that the tool requires user interaction (the user must paste content into an external AI system), and it warns about token limits and the optional skipTokenCheck. It also explains the code extraction mechanism using Probe, adding transparency about internal behavior. No contradictions with annotations exist since none are provided.

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 structured with clear sections and front-loads trigger conditions, but it is lengthier than necessary and repeats the same trigger information in the initial paragraph and the bullet list. Some emoji formatting adds visual noise. While every section provides value, the redundancy prevents a higher score.

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?

For a tool with no output schema and two parameters, the description comprehensively explains the workflow: when to invoke, what the question must include, the user's required next step, and token limit considerations. It gives enough context for an agent to use the tool correctly and set expectations. The lack of explicit output format is compensated by the described interaction flow.

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?

The input schema already covers both parameters comprehensively, describing the question string requirements and the skipTokenCheck flag with its caution. The description adds some emphasis on comprehensiveness and file paths, but it mostly restates the schema's guidance. Since schema coverage is 100%, the baseline of 3 is appropriate; the description does not provide additional parameter-level details beyond the schema.

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's purpose: 'formats complex questions for the BigBrain system using intelligent code extraction.' It specifies trigger conditions including explicit 'big brain' mentions and situations like being stuck or losing context, making the scope unambiguous. Though no siblings are listed, the description itself defines the tool's unique role as an external AI consultation conduit.

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 provides explicit WHEN TO USE bullets, including 'User explicitly asks for big brain', 'You are stuck in a loop', and 'Need fresh external AI perspective'. It also states the tool requires user interaction to complete the workflow, effectively telling the agent when and how to use it. No alternatives are named, but the trigger conditions serve as strong guidance.

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