Think About Task Adherence

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

Annotations indicate readOnlyHint=true and destructiveHint=false, which already convey that this is a safe, non-destructive operation. The description adds context about its role in ensuring task adherence before code modifications, which is useful behavioral insight beyond the annotations. However, it does not detail aspects like potential side effects, performance implications, or error handling.

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 and front-loaded, with three sentences that directly address purpose and usage without unnecessary details. Each sentence adds value, such as the specific trigger conditions and mandatory usage before code changes, making it well-structured and efficient.

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 (low, with 0 parameters), rich annotations (readOnlyHint, destructiveHint), and the presence of an output schema, the description is complete enough. It explains the tool's role in task adherence and when to use it, which aligns with the structured data. However, it could slightly enhance completeness by mentioning what the output schema returns, though this is not strictly necessary.

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 tool has 0 parameters, and schema description coverage is 100%, so there is no need for parameter explanation in the description. The description appropriately does not discuss parameters, which is efficient, but since there are no parameters, a baseline of 4 is applied as it fully compensates for the lack of parameter details.

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 states the tool's purpose as 'Think about the task at hand and whether you are still on track,' which is a clear action but somewhat vague in scope. It does not specify what resources or data it operates on, and it does not distinguish itself from sibling tools like 'think_about_collected_information' or 'think_about_whether_you_are_done,' making it less specific than ideal.

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 usage guidelines: 'Especially important if the conversation has been going on for a while and there has been a lot of back and forth' and 'This tool should ALWAYS be called before you insert, replace, or delete code.' This gives clear context for when to use it, though it does not explicitly state when not to use it or compare it to alternatives like other 'think' tools.

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