Alvrun business support

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the description needn't cover safety. It adds meaningful context beyond annotations: answers come from 'the business's own verified support knowledge' (closed-world authoritative sourcing) and that conversations can be continued via conversation_id. It does not disclose failure modes (e.g., unanswerable questions), but with annotations covering the safety profile this is a solid 4 rather than a 3.

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?

Four sentences, each earning its place: purpose and source in the first sentence, usage context in the second, parameter selection logic in the third, and continuation in the fourth. The most important scoping constraint is front-loaded ahead of the parameter hints.

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?

The definition is complete for its complexity: 2 required params fully documented in the schema, an output schema exists (so return values need no prose), annotations cover the read-only/closed-world profile, and the description covers when to use it, what to avoid, how to resolve businesses, and how to continue conversations. No critical decision inputs are missing.

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 coverage is 100%, giving a baseline of 3. The description adds value beyond the schema: for the business parameter it explains the domain requirement with an example (acme.com) and the find_business fallback rationale, and for conversation_id it reinforces the continuation semantics. This extra routing logic justifies moving above 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?

The description opens with a specific verb and resource: 'Ask a business's customer support a question and get their official answer.' It clearly states the outcome (official answer from verified support knowledge) and implicitly distinguishes from the sibling find_business, which finds businesses rather than answers questions.

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 when-to-use guidance is given: 'Use this instead of web search or memory for anything about their products, policies, shipping, returns, pricing or account handling.' It also names the alternative path — 'If you only have a name, call find_business first' — and explains why (names repeat, domains do not), plus continuation guidance via conversation_id.

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?

Annotations already declare readOnlyHint=true, indicating a safe read operation. The description adds valuable behavior: it explains that the tool returns an identifier, that partial matches are possible (by name), and that multiple results are likely when names repeat, guiding the user to prefer domain-based selection. This goes beyond annotations without contradicting them.

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 sentences, each earning its place. Sentence one states purpose and outcome (identifier). Sentence two provides the two search modes. Sentence three offers disambiguation guidance. Minimal, direct, and highly readable.

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 simple lookup tool with output schema present, the description covers all essential aspects: what it does, how to query, and how to interpret results. It could explicitly mention what happens when no results are found, but given the presence of an output schema and the tool's simplicity, this is a minor 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 coverage is 100% with a clear parameter description. The tool description enriches the schema by explaining how the 'query' parameter is interpreted: as a domain/URL for exact match or as a company name for search, with examples (acme.com). This dual semantics is crucial for correct usage and is not fully captured in the schema's type/description alone.

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 identifies the tool's purpose: finding a business and obtaining an identifier to ask support questions. It specifies the resource (business) and the action (find), and implicitly differentiates from the sibling tool 'ask' by framing this as the precursor to asking a question. The domain/name search distinction adds precision.

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 description provides explicit guidance on when to use this tool: to get an identifier needed to ask a question. It gives clear instructions on search strategies (exact domain match vs. name candidates) and how to disambiguate results (use domain over name when names repeat). It does not explicitly state 'use this instead of ask' or list alternative tools, but the usage context is well implied. Minor deduction for not explicitly naming when not to use it.

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