cpg_think

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

No annotations are provided, so the description carries the full behavioral disclosure burden. It transparently states the ephemeral nature, the promotion mechanism that persists to an OBSERVATION node, and the requirement to pair obs_type with promotion. It does not address return behavior, but the core persistence semantics, side effects, and conditionality are disclosed.

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?

Three sentences total, with the core role ('ephemeral reasoning scratchpad') front-loaded, followed by the promotion condition and the routing rule. Every sentence contributes a distinct piece of information with zero filler.

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 description gives agents the essential operational context: ephemeral scope, promotion when needed, and explicit alternative routing. The only notable omission is what the tool returns or what an OBSERVATION node means downstream, but given the 100% schema coverage and the strong usage routing, the agent has enough to invoke it correctly.

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 baseline is 3. The description adds meaningful parameter semantics by clarifying that promote_to_=observation with obs_type is the persistence condition, and qualifying which content qualifies (directly perceived data) versus content that belongs in record_belief. This goes beyond what the schema states about the parameters.

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 opens with 'Ephemeral reasoning scratchpad', stating a specific role and resource immediately. It further distinguishes the tool from record_belief by explicitly stating that predictions and hypotheses go through record_belief, not here.

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 gives explicit conditions for persisting: 'Use promote_to=\'observation\' with obs_type to persist' and when to do so ('when the thought captures directly perceived data (tool output, file read, etc)'). It also gives direct when-not instructions by routing predictions and hypotheses to record_belief, leaving no ambiguity about the alternative.

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