flywheel_stats

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

Because no annotations are provided, the description carries the full burden of behavioral disclosure. It does provide meaningful interpretation of the metrics and a failure signal. However, it never explicitly states that this is a read-only stat retrieval, whether values are computed live, or what effect if any the call has, leaving some assumptions implicit.

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 brief and front-loads the core question of whether memory is compounding. The metric names and their interpretation are packed into two focused sentences, though the opening fragment is slightly ungrammatical.

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 parameterless stats tool with an output schema, the description covers the essential interpretation and a key failure mode. It does not explicitly describe when or how often to invoke the tool, or state that it is a read-only operation, but the overall picture is adequate for a simple stats check.

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 zero parameters, so the schema already fully covers parameter semantics. The description adds value by explaining what the metrics mean and how to judge them, which is beyond what an empty parameter schema could provide.

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 identifies the tool as a check on whether the memory flywheel is compounding surroundly, and pinpoints the key metrics to inspect. It lacks an explicit verb such as 'returns' or 'reports', but the intent is clear and it is not confused with siblings like record_answer or get_selector_hints.

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?

There is no explicit when-to-use guidance or mention of alternative tools. The interpretation that a `selectors_suggested` of 0 after real runs indicates a logging problem implies a monitoring use case, but it does not tell the agent when to call this tool versus related diagnostics like setup_status or guard_status.

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