inference_metrics

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

With no annotations provided, the description carries full burden. It explicitly states 'Read-only, no arguments' and clarifies that it reflects prism_infer delegation usage only. This provides sufficient behavioral disclosure beyond what annotations would supply.

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 two sentences: the first lists the returned metrics, the second clarifies scope and exclusions. It is concise, front-loaded, and every sentence adds value with no waste.

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?

Although no output schema exists, the description enumerates the types of metrics returned (call count, split, token totals, per-model breakdown, latency). This provides reasonable completeness for a read-only metrics tool, though a brief note on response format would slightly improve it.

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 input schema has no parameters, so baseline is 4. The description does not need to add parameter meaning, and it appropriately explains that no arguments are needed.

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 returns inference metrics for the current session, listing specific metrics (call count, local vs cloud split, token totals, per-model breakdown, average latency). It distinguishes itself by explicitly noting what it does not cover (Claude's own token spend), making the purpose unambiguous.

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 provides clear context for when to use the tool (to get inference metrics) and what not to use it for (host model's token spend, directing to /cost instead). However, it does not explicitly mention when-not or alternative sibling tools, though the only related sibling is prism_infer, which is different.

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