calibrate_decay

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

With no annotations, the description carries full burden. It mentions the input (retrieval history) and the formula (median survival span -> decay rate), but does not disclose whether this mutates the system's memory parameters, requires any prerequisites, or what side effects may occur. This is a significant transparency gap for a calibration operation.

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, well-structured sentence that conveys the purpose and the core transformation without any wasted words. Every part earns its place.

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 is adequate but leaves gaps: no mention of the output format, whether it writes back to the system, or how it relates to similar tools like curve_fit. Given the lack of annotations and output schema, more behavioral context would be beneficial, but the core concept is understandable.

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?

There are zero parameters, and the schema coverage is trivially 100%, so the baseline is 4. The description adds meaning beyond the schema by explaining the implicit input (real retrieval history and median survival span), which helps the agent understand what data is used.

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 'calibrate', the object 'forgetting rate', and the source 'real retrieval history', with the transformation 'median survival span -> decay rate' providing specific scope. This distinguishes it from siblings like curve_fit or next_interval by emphasizing calibration from historical data.

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?

It provides clear context: use when you have real retrieval history and need to compute the decay rate. It doesn't explicitly exclude alternatives or name them, but the phrasing implies when it is appropriate. Lacks explicit 'when not to use' guidance.

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