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

With no annotations, the description carries full behavioral disclosure weight. It discloses idempotency on entry_id, validation against the Landauer floor, and rejection of physically impossible claims. It also explains energy and carbon calculations. It does not cover permissions or error handling, but the described behaviors are valuable and non-obvious.

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, front-loaded with the primary purpose. The second sentence packs the formulas and validation logic without unnecessary words. Every part contributes meaning.

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 the 9-parameter schema and the existence of an output schema, the description provides strong context for invocation: it explains core input relationships, validation, and idempotency. Missing details about price/task are minor and likely covered by defaults. Overall, it is complete enough for effective use.

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 0% description coverage, so the description must compensate. It does so by explaining the relationships: energy_j = power_w * duration_s, carbon_g follows grid_intensity_g_per_kwh, and bit_ops validation using temperature_k. It also mentions entry_id for idempotency. However, it omits semantics for price_minor_per_kwh and task, which are less critical.

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 begins with a specific verb+resource: 'Record a unit of agent compute work.' It clearly distinguishes from sibling tools like record_inventory by focusing on compute work and energy/carbon accounting. The inclusion of formulas and validation adds specificity beyond the tool name.

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 clearly indicates this tool is for recording compute work events. It provides enough context (energy/carbon tracking, idempotency, Landauer validation) that an agent would know when to use it. However, it does not explicitly name alternatives or state when not to use it, but the context is unambiguous.

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