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

Beyond the annotations (readOnlyHint=true, openWorldHint=true, idempotentHint=true), the description adds significant behavioral context: answers are 'grounded in verified rules' and pass a 'rigorous verification pipeline', it is not a general search, and it explicitly discloses that the SME (conduit) is compliance-only and does not provide clinical values or record content. This is exactly the kind of behavioral detail agents need.

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 long but meticulously structured: opens with a precise purpose, then usage triggers, then source details, then scope, then a routing directive. Each section is dense with useful information and there is no redundancy. The length is justified by the tool's domain complexity and strict scope boundaries.

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 the tool's complexity (a domain expert with strict compliance-only scope and only one available source), the description covers every aspect an agent needs: when to use, what it does, what it does not do, the available source, and how to route questions. The lack of an output schema is acceptable since answers are open-ended queries; the description already sets expectations about verification and sourcing.

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%, so the baseline is 3. The description adds value by explaining the sme_source parameter ('Available SME sources: conduit... defaults to conduit') and providing context on how to use the context parameter (e.g., 'I'm creating a social media post about cleanroom best practices'). It also clarifies the companyId is for company-scoped actions. This extra context elevates it slightly 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 clearly states the tool's purpose: 'Query an external Subject Matter Expert (SME) AI for verified domain knowledge.' It explicitly distinguishes from general search ('this is NOT a general search, it's consulting a domain expert') and names the specific resource (conduit for USP 795/797/800 compliance). The scope section further differentiates it from clinical tools.

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 explicit 'Use this when:' list with four concrete scenarios, plus a detailed SCOPE section with IN/OUT boundaries and a specific routing rule ('pharma / USP 795·797·800 / BUD / board-of-pharmacy COMPLIANCE fact you must get right → call query_sme'). It also states what NOT to do (never dosing or clinical judgment) and what it cannot supply (clinical values), leaving no ambiguity about when to invoke.

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