conduyt_import_preflight

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

No annotations are provided, so the description carries the full burden, and it does disclose the returned diagnostic categories (criticalWarnings variants, duplicate/existing-match estimates, invalid emails, DNC/litigator hits, SMS readiness, plan-limit impact). It also implies a side-effect-free check via 'pre-check ... BEFORE running it' and 'same engine the import wizard uses'. It stops short of explicitly declaring read-only/no-mutation behavior, payload size limits, or rate constraints for large arrays.

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, front-loaded with the action and its precondition, then a compact enumeration of what comes back. Every clause (the specific warning types, the wizard-engine provenance, the sibling pointer) adds decision-relevant information; nothing is filler.

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?

With no annotations and no output schema, the description compensates well by enumerating the result categories and the intended call sequence. Gaps remain: it does not address large-payload handling for the emails/phones/rowIdentifiers arrays, nor the contacts-only framing against an objectType enum that spans companies and opportunities. For a 9-parameter read tool this is close to sufficient but not airtight.

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 all nine parameters are documented in the schema itself; the description adds only indirect meaning by naming 'create-only duplicate skips' and 'double-mapped columns', which hint at how importMode and mappedFields drive the warnings. No syntax, ordering, or fallback guidance (e.g. omitting rowIdentifiers degrades to a conservative estimate) is restated in the description. Baseline 3 is appropriate.

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?

States a specific verb and resource ('pre-check a contact import') and distinguishes itself from the sibling that actually performs the write ('call this before conduyt_ai_import_contacts'). An agent knows exactly what this tool is versus the import tool. Minor caveat: it frames the tool as contact-only while objectType also allows opportunities/companies, but the core purpose is unambiguous.

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?

Explicitly says to call it 'before conduyt_ai_import_contacts on any sizeable list', naming the alternative and the triggering condition. It does not state when to skip (e.g. tiny lists) or what other preflight alternatives exist, and 'sizeable' is left unquantified.

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