deep-thinker

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

With no annotations provided, the description carries full burden for behavioral disclosure. It describes key traits: the tool can view states, get suggestions, switch strategies, and receive guidance, with automatic detection of stuck states. However, it lacks details on permissions, rate limits, side effects (e.g., whether switching strategies affects ongoing processes), or response format. The description adds value but is incomplete for a tool with behavioral complexity.

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 appropriately sized and front-loaded, listing core operations in the first sentence and adding context in the second. Every sentence earns its place by explaining functionality and automatic features without redundancy or fluff. It efficiently conveys the tool's scope in two clear sentences.

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 moderate complexity (3 parameters, no annotations, no output schema), the description is somewhat complete but has gaps. It covers what the tool does and hints at usage, but lacks details on behavioral traits like side effects or response format. Without an output schema, the description should ideally explain return values, but it doesn't. It's adequate for basic understanding but not fully comprehensive.

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 description coverage is 100%, so the schema already documents all parameters well with enums and descriptions. The description doesn't add specific parameter semantics beyond what's in the schema, but it provides high-level context that aligns with the parameters (e.g., 'switch strategies' relates to the 'action' and 'strategy' parameters). With 3 parameters and full schema coverage, the baseline is 3, but the description's alignment with parameters justifies a slight bump.

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 with specific verbs (view, get, switch, receive) and resources (thinking state, strategy suggestions, guidance). It distinguishes metacognitive operations from likely siblings like 'think' or 'evaluate' by focusing on monitoring and adjusting reasoning processes rather than direct thinking or evaluation. However, it doesn't explicitly differentiate from all siblings like 'reset' or 'prune'.

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 usage context through 'automatically detects stuck states and recommends actions,' suggesting this tool is for overcoming reasoning blocks. However, it doesn't explicitly state when to use this versus alternatives like 'think' for direct reasoning or 'reset' for restarting processes. No clear exclusions or named alternatives are provided.

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