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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuinely new behavioral context: it operates purely over a saved document with no evaluation or recomputation, and it defines the semantics of absent data as a limit state rather than a negation. It does not cover pagination or rate/latency behavior.

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 resource and read-only framing are front-loaded, and little is pure filler, but the operation breakdown is delivered as one dense, dash-separated run-on that is hard to parse. Structure suffers even though information density is high.

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 format need not be explained. But for a complex 11-parameter tool with nested objects and a oneOf constraint at 0% schema coverage, the description omits pagination, indexing, bundling and source-selection semantics, which an agent would need to invoke it correctly in non-trivial cases.

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% across 11 parameters, so the description carries real weight: it maps each operation to its inputs (slice selectors for query/rule/position/node, diff via against, locate by StableId). However, several top-level parameters — page/cursor/budgetBytes, index, bundle, sources, context, snapshot — are never mentioned, leaving meaningful gaps.

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 names a specific verb (inspect, read-only) and resource (a SAVED evaluation document) and enumerates the four operations — summary, slice, diff, locate — each with its own scope. It does not directly contrast with siblings like law_ask or law_explain, but it does name law_ask(proof=true) as the upstream source, which implicitly differentiates inspection from evaluation.

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 gives a clear when-to-use condition: the source must be an evaluation from law_ask(proof=true) or an answerResource, and it emphasizes that nothing is evaluated or recomputed here. It also supplies interpretation guidance ('missing data is a limit state, never a negation'), though it states no explicit when-not or named alternatives.

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