AILegal — verified legal provisions for agents

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

With no annotations, the description carries the full behavioral burden. It usefully discloses that results include verified provisions with official-source links and that the tool refuses when no norm exists, but it does not state permissions, read-only behavior, coverage limits, or what 'verified' operationally means.

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 short, front-loaded, and every sentence adds information: purpose, jurisdiction values, and the no-norm refusal behavior. The telegraphic 'jurisdiction:' fragment is still clear and wastes no space.

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?

For a three-parameter tool with no annotations and no schema descriptions, the description covers the main purpose, jurisdiction values, and refusal condition. However, it leaves locale unexplained and does not route the agent between this tool and its two siblings, so it is only minimally complete for correct invocation in ambiguous 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%, so the description should compensate. It provides valuable meaning for jurisdiction by listing accepted values (ru|in|us|uk|ca|hk), which the schema does not enforce as an enum, and implies that text is the legal situation to describe, but it says nothing about locale.

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 clearly states the resource and outcome: describe a legal situation and receive verified provisions with official-source links. It does not explicitly distinguish this tool from siblings oracle_lookup and verify_citation, so an agent must infer the boundary.

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 phrase 'Describe a legal situation' implies the use case, and 'Returns a refusal when the corpus has no norm' clarifies an important limitation. However, there is no explicit guidance on when to use this tool instead of oracle_lookup or verify_citation, and no when-not-to-use exclusions.

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

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

With no annotations, the description carries the full disclosure burden, and it does deliver one genuinely non-obvious behavioral fact: an empty list signals corpus absence rather than an error — important for agent branching. Beyond that it says nothing about ranking of results, what "verified" concretely guarantees, corpus scope, or any rate/permission constraints.

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 no filler, and the empty-result semantics are stated up front where an agent will read them. The only waste is the 'Legal Oracle:' label, which occupies prime opening position without adding information.

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?

Because an output schema exists, the description is not obligated to explain return structure, and it correctly covers the one edge case an output schema cannot express (empty list meaning). However, for a three-parameter retrieval tool with zero schema documentation and no annotations, the missing limit semantics and undefined notion of 'verified' leave real gaps.

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 all three parameters are bare in the schema, and the description only partially compensates: it clarifies that jurisdiction is optional and acts as a filter. The required query parameter is only implied, and the limit parameter and its default of 5 are never mentioned, leaving an agent to guess truncation behavior.

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?

"Which verified provisions relate to a query" states the resource (verified legal provisions) and the operation (retrieval by query relevance) clearly enough that an agent can distinguish it from a citation-verification sibling. The 'Legal Oracle:' branding prefix is noise, and it never explicitly contrasts itself with verify_citation or legal_breakdown, so it stops 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?

The only usage-adjacent content is "Optional jurisdiction filter," which describes a parameter default rather than when to call this tool. There is no guidance on when to prefer it over legal_breakdown or verify_citation, no prerequisite steps, and no exclusions.

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

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

With no annotations, the description must carry the behavioral burden. It does disclose that verification is against a 'verified corpus' (implying read-only, no mutation) and explains the meaning of a negative result, but says nothing about latency, coverage limits, or what happens when jurisdiction is omitted.

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?

Two short sentences, front-loaded with the core question and followed by the decision rule. The 'Legal Oracle:' prefix is mildly decorative but costs little.

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-field documentation is not required, and the description usefully pre-explains the found flag. However, for a three-parameter tool with zero schema coverage, the unaddressed jurisdiction parameter leaves a real gap.

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 only partially does: 'code/article pair' signals those two parameters form the citation, but the third parameter, jurisdiction, is never mentioned and no formats or defaults are clarified.

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 gives a specific verb and resource ('does this citation exist in the verified corpus'), which tells an agent exactly what is checked. It implicitly distinguishes itself from siblings like oracle_lookup or legal_breakdown by framing this as a yes/no existence check, though it never names those siblings.

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 states a clear usage condition: 'Use before relying on any code/article pair,' plus the consequence rule 'found=false means do not rely on it.' It lacks explicit guidance on when not to use it or which sibling to prefer for broader lookups.

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