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

Annotations already carry idempotentHint=true and destructiveHint=true, so the bar for description disclosure is lower. The description adds useful boundary context by listing operations it does not perform. However, for a mutation tool flagged destructive, it does not mention that creating a questionnaire may overwrite an existing one or require idempotency-key reuse, which the annotation set only partially signals.

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 sentences with zero filler. The primary action and its limit are front-loaded, and the second sentence efficiently enumerates exclusions that clarify the tool's boundary. Every clause earns its place.

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 tool with three required params, nested objects, a destructive hint, and no output schema, the description is adequate but thin: it clarifies scope and input kind but stays silent on return values, failure modes, and the destructive implications flagged by annotations. The idempotencyKey description in the schema relieves some of this burden, but the overall definition leaves the agent inferring a fair amount.

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 67% (projectId and idempotencyKey have descriptions; the questionnaire object's property itself lacks a summary, though its nested fields are well documented). The description adds the 'client-supplied' framing and the 100-question cap, which mirrors the schema's maxItems. It adds modest semantic value but does not compensate for the missing top-level questionnaire description.

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 uses a specific verb ('Create'), a resource ('questions for a dossier'), and a concrete limit ('up to 100'), then distinguishes itself by spelling out what it does NOT do: import a workbook, attest signatures, or approve answers. This clearly separates it from siblings like helvabase_upload_sources, helvabase_answer_questionnaire, and helvabase_apply_business_claim_approval without the agent needing to open schemas.

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 gives clear exclusions (no workbook import, no attestation, no approval) and implies the intended input ('client-supplied questions'), but it never names alternative tools or states the conditions under which an agent should pick this tool over related ones. The when-to-use is only implied, not explicit.

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