get_learning_metrics

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

With no annotations, the description carries full burden. It adds context about required read scope, governance by Arbiter constitutional policy, and a cryptographic receipt. However, it does not disclose whether the tool is idempotent, cached, or has rate limits, and the term 'ProofLink cryptographic receipt' is left unexplained.

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 extremely concise: two sentences with no redundancy. The first sentence states what the tool does; the second adds essential prerequisites and policy context. No wasted words.

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 a simple no-parameter tool, the description covers the main output items and access requirements. However, it lacks details on return format, pagination (if any), and does not explain the receipt or policy implications. Without an output schema, more description of the result structure would be beneficial.

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 schema coverage is 100% (no parameters to document). The description does not need to add parameter details. It provides minimal but acceptable context.

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 retrieves Learning Arbiter cycle metrics with specific enumerated items (processed, promoted, rejected, known patterns). The verb 'Get' and resource 'Learning Arbiter cycle metrics' provide clear purpose. However, it does not differentiate from sibling get_* tools like get_learning_queue beyond the metric names.

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 mentions a required scope (learning:arbiter:read) but provides no guidance on when to use this tool versus alternatives like get_learning_queue or other metric-related tools. No context on prerequisites or exclusion criteria is given.

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