Comfy compute delivered

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), but the description adds real behavioral content: on partial index reads the response is live:false with outcome compute_unknown and a reason, "never a number", and results are "served verbatim". That failure-mode disclosure is exactly what annotations cannot express.

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 purpose is front-loaded in the first clause and the exclusion and error semantics follow in order. It is dense and jargon-heavy ("cumulative InfinityComputeDestination.totalDelivered", the "Served verbatim." fragment), but nearly every clause carries information an agent needs.

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 no output schema, the description takes on the burden of describing returns and does so: total in OG, agent count, per-token rows with their fields, and a basis sentence. Combined with the failure-mode explanation, an agent can call this correctly and interpret both success and degraded responses.

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 takes zero parameters, so there is nothing for the description to disambiguate; baseline applies. The description instead spends its words on the return shape, which is the right choice here.

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 names a specific resource and scope: cumulative compute delivered per pool, all time, from the points engine's Infinity index. It explicitly excludes misreadings ("not a remaining balance or inference bought"), though it never names the sibling comfy_agent_compute as the alternative for per-agent views.

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?

Usage context is implied rather than stated: "all time" and "from the points engine" tell the agent when this metric applies, and the negative clause rules out balance/inference questions. There is no explicit "use this instead of comfy_agent_compute when..." routing against a very crowded sibling set.

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