Comfy agent compute

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and non-destructive, so safety is covered. The description adds real value beyond that by disclosing null/absence semantics: router is null with a reason, unknown tokens yield data:null, and unreadable indexes yield live:false with outcome compute_unknown. That is substantive failure-mode context, though some terms remain 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?

Two long, dense sentences that front-load return-field jargon before establishing the action. The null-handling details are useful but the first sentence crams compute_og, pool, ladder tier, and basis sentence without defining them. Wasteful in style, not length.

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 does attempt to describe the return shape (compute_og, pool, ladder tier, basis sentence, router) and its null states, which is the right burden to pick up. But the field explanations lean on undefined internal terms, leaving an agent unsure what the values actually mean or how to interpret them.

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 is a single required parameter with 100% schema description coverage (contract address, 0x… 40 hex chars), so the schema already carries the semantics. The description adds nothing about the token argument, which is acceptable given the coverage but earns no above-baseline credit.

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 identifies the resource as one token's delivered compute from a points engine and lists the fields returned, so an agent can infer it is a per-token compute lookup. However it is a noun phrase, not a verb+resource statement, and it never differentiates itself from the sibling comfy_compute_funded, which likely overlaps. Undefined jargon like 'Infinity index' and 'ladder tier' further blurs the purpose.

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?

There is no guidance on when to call this versus comfy_compute_funded or any other sibling, and no stated prerequisites (e.g. token must be launched). The edge-case sentences describe outcomes, not call conditions. An agent must guess the selection criteria.

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