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

Beyond the annotations (readOnlyHint, openWorldHint=false, idempotentHint=false), the description discloses that sourceSchemaContentHash is compared loudly against the pin, that the confidence number is consumed by the package's EvidencePolicy rather than this tool or the engine, and that downstream rows are fully computed with a proof graph on the same snapshot. That is meaningful behavioral context not derivable from annotations. No auth/rate-limit detail, so not a 5.

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 scope and exclusions are front-loaded and each sentence carries boundary or behavioral information rather than filler. Density of jargon (arbre typé, manifeste des extensions jusqu'à TRUE) makes it heavier than needed, but nothing is redundant.

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 spelled out, yet the description still frames the output shape (typed tree + manifest). Given 5 parameters, 4 required, and nested objects, the description covers the workflow and responsibility boundaries adequately. Minor gaps around lifecycle/idempotency expectations (idempotentHint=false) remain.

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 adds role context for two parameters (binding as a pinnable object, sourceSchemaContentHash as the real schema fingerprint compared with the pin) but says nothing about goal, package, or legalTime beyond the schema. The marginal gain is real but limited, so it stays at the baseline.

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?

Front-loads a specific verb and resource: build a necessary condition (superset) for pre-selecting rows from an external source, and clarifies the output is a typed tree plus manifest, not a legal answer and not SQL. This cleanly separates it from answer-producing siblings like law_ask and law_answer_capabilities. It does not fully distinguish it from data-oriented siblings such as law_query or law_search, keeping it short of a 5.

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?

Explicit exclusions are stated: it is NOT a legal answer and NOT SQL, and business facts with provenance (origin, document, citation, extractor) are directed to law_ask rather than here. This gives real routing context. It lacks an explicit positive 'use this when...' statement contrasting with law_query/law_search, so it falls just under a 5.

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