judge_get

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

With no annotations, the description carries the entire behavioral burden and discloses very little: it does not say whether the call errors out on an ambiguous ID or returns something partial, whether there are permissions or rate limits, or what happens with an unknown ID. Only the source-requirement rule is surfaced, and even that leaves the failure mode unspecified.

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?

A single short sentence with the conditional rule placed after the purpose, no filler, and nothing repeated. It is efficient, though its brevity is close to under-specification rather than disciplined concision.

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?

An output schema exists so return values need not be explained, but with no annotations and zero schema coverage the description should do more: it never defines what an "item" is, gives no ambiguity-resolution or error behavior, and leaves item_id format unknown. The agent knows a source may be needed but not much else.

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 0%, so the description must compensate, and it partially does by explaining the conditional necessity of `source` — meaningful semantics the bare anyOf/null schema does not convey. `item_id` is left entirely uncharacterized (format, expected identifier scheme), so half the parameters remain undocumented.

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?

"Read an item" gives a verb plus a resource, but "item" is never defined in domain terms, so the agent cannot tell what kind of object is being fetched. It is distinguishable from judge_ingest/judge_pending by being the read path, but only weakly, since the resource noun carries no specificity.

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 clause "source is required when the ID exists in multiple sources" is a real conditional rule for one parameter, which is more than nothing. However, there is no statement of when to reach for judge_get versus judge_pending or judge_ingest, and no guidance on what to do when the ID turns out to be ambiguous.

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