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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds one genuinely useful behavioral fact beyond that: a missing match means absence from the indexed lookup results, which tells the agent how to interpret a negative result. It says nothing about what a successful response contains, what happens when several identifiers are supplied at once, or how ambiguity is resolved.

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?

Three short sentences with the retrieval capability front-loaded and the negative-result caveat last, which is the right ordering. No filler or repeated content, though the identifier list would read better if tied to specific parameters.

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?

There is no output schema, so the description is the only place an agent could learn what a hit looks like, and it does not say. Combined with zero schema coverage on three optional parameters and no statement of what happens on ambiguous or multi-identifier input, the definition covers the happy path but leaves meaningful gaps for a lookup tool.

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 carry the load for id, court and identifier, and it only partially does. It explains the court filter's accepted form (codes like TC and TS, or exact unambiguous catalog names) and lists the identifier schemes, but it never maps which scheme belongs to `id` versus `identifier`, leaving the two most confusable parameters undifferentiated.

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 ("Retrieve a judgment") and enumerates the identifier schemes it accepts (stable ID, ECLI, ROJ, decision number, case number), which tells an agent this is an identifier-based fetch rather than a query. It does not explicitly name search_decisions or read_decision as the contrasting siblings, so the differentiation is implicit rather than stated.

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 is only implied: the enumeration of identifier types signals "use this when you already hold a known identifier," but the description never says so outright, nor when to prefer search_decisions or read_decision instead. There are no stated prerequisites, no note that all three parameters are optional, and no guidance on which to supply.

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