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

With no annotations, the description carries the full behavioral burden. It usefully discloses ordering ('newest first'), the presence of recomputable digests, and that the log is 'immutable, append-only', which tells the agent the underlying data is read-only. However it says nothing about pagination behavior, the meaning of the limit cap, or auth requirements.

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 core purpose is front-loaded in a single dense sentence, which is good, but the parenthetical kind lists and the opaque 'ask for the genome frames' clause add length without proportional clarity. Some trimming would improve the ratio of signal to words.

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?

For a filtered-list tool with no output schema, no annotations, and three parameters at 33% coverage, the description covers what the tool returns and its ordering but leaves return shape, pagination, and the limit/id interaction unspecified. Adequate as a minimum-viable definition, but not 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 coverage is only 33% — only `id` is documented. The description adds the intent behind `kind` ('Filter by kind') and hints at a mode to 'ask for the genome frames', but leaves the `limit` parameter unexplained and does not clarify whether `id` and `kind` are mutually exclusive. It partially compensates for the coverage gap but not fully.

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 states a concrete verb and resource — retrieving every decision the judge made for a layer — and enumerates the decision kinds (pad picks, skill rankings, assembles, grades, study batteries), so an agent knows exactly what data comes back. It stops short of differentiating itself from close siblings like taifoon_judge_compose or taifoon_judge_ref, which it must be distinguished from.

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?

It offers partial direction ('Filter by kind') which implies how to narrow results, but gives no explicit when-to-use guidance, no exclusions, and does not name which sibling to pick instead for composing or referencing a decision. The trailing 'ask for the genome frames' is too cryptic to function as usable guidance.

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