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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals that the critic is deterministic, that consensus among nine cells is required, that cells report generative:0, and that the output is a score0-1000 plus integer span/pitch deltas. The failure consequence is cryptic, but the tool's core behavior is unusually well disclosed.

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 and output details are front-loaded and compact, but the middle sentence is dense and cryptic ('nine cells', 'fleet's byte-identity is gone', 'generative:0') without adding clear, actionable invocation guidance. It is short, but not every phrase earns its place.

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?

The description explains the output format and some behavioral constraints, but it leaves the meaning of parameters such as h/n/t/w/kind largely unexplained and does not state what happens if consensus fails. For a tool with no annotations and no output schema, a little more framing around inputs and failure behavior would make it complete.

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 high at 86%, so the schema already provides at least terse descriptions for most parameters. The description does not add substantial per-parameter meaning; it only mentions 'span/pitch deltas' in the output context. Thus it sits at the baseline for high schema coverage.

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 a specific verb and resource: 'Grade a rendered frame and return integer corrections.' It also states the scoring range (0-1000) and integer return type. It does not explicitly differentiate from sibling tools like the verify_* family, so it stops short of a 5.

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 phrase 'Grade a rendered frame' implies when the tool should be used, and 'deterministic, not a model' hints that it fits critic/consensus work rather than generative or model-based evaluation. However, there is no explicit when-to-use or when-not-to-use guidance and no mention of alternative sibling tools, leaving the choice largely to inference.

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