marrow_model_usage

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

No annotations are provided, so the description carries the transparency burden. It does disclose an important behavioral constraint: the tool must not receive raw prompts or sensitive content. However, it does not mention side effects, persistence, idempotency, or what the tool returns, leaving significant behavioral gaps.

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, front-loaded with the main action and usage context. The safety instruction is essential and earns its place. No filler or repetition.

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?

With 17 parameters, no output schema, and no annotations, this description is underspecified. It gives the tool's general purpose but doesn't explain how to populate the many optional fields (e.g., cost_usd, latency_ms, estimated_tokens_saved) or what the recorded data is used for. It is minimally viable but lacks operational detail.

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 only 18%, and the description does little to compensate. It mentions 'model token usage' and 'value proof,' which hints at the token and cost parameters, but 17 parameters are mostly undocumented, and their meanings must be inferred from names alone.

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 the specific verb 'Record' and a clear object: 'compact model token usage for value proof.' This distinguishes it from siblings like marrow_value_report, which implies reporting rather than recording.

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?

Explicitly states when to use the tool: 'Use when the harness exposes provider/model token counts.' It also provides an exclusion by saying 'Do not send raw prompts, completions, tool logs, secrets, or customer content.' It does not name alternative tools, but the context is clear.

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