check_treatment

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

With no annotations, the description carries full behavioral burden and handles it well: signals are disclosed as conservative, non-authoritative, heuristic, and scanned from the citing sentence alone. It also reveals ordering behavior (possible-negative and distinguished surfaced first) and the risk that treatment words may refer to a different case.

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 description is front-loaded with the one-line definition, followed by mechanics, ordering behavior, and a necessary caveat. Every sentence earns its place; the only slight redundancy is between 'conservative, non-authoritative' and 'heuristic,' but that emphasis is justified for a legal-research tool.

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?

Given an output schema exists and parameter coverage is complete, the description supplies the missing contextual risk factors: heuristic signals, non-authoritativeness, sentence-level scanning, and not being a good-law verdict. An agent has enough to decide when to use this tool and how to interpret its results.

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 100%, so the baseline is 3. The description does not add parameter-level details beyond the schema, though its discussion of truncation and ordering is relevant to the limit parameter. No compensation needed because the schema already documents citation, limit, and scan_limit clearly.

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?

Description states a clear verb and resource: 'how later opinions have treated a case' and describes the specific output: citing sentence, paragraph, and treatment signal. The KeyCite/Shepard's-style framing gives it a distinct identity among sibling tools like get_citing_opinions or get_subsequent_history.

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?

Provides strong usage boundaries: explicitly warns it is NOT a 'still good law' verdict and instructs the agent to read the returned sentence and full citing opinion before relying on it. It does not name alternative tools for other citator needs, so it stops short of fully explicit routing.

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