create_export

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

Beyond the readOnly/idempotent/non-destructive annotations, the description adds genuinely new context: authentication is required, the caller's suppression list is applied to output, an export audit is logged, and no credits are consumed. Minor tension: 'records an export audit' implies a server-side write while readOnlyHint=true is declared, though this is audit logging rather than record mutation. It still omits what is actually returned (URL vs job id) and any expiry behavior.

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 dense sentences with the core action front-loaded and no filler. The trailing API-key warning is slightly tangential but is a legitimate security constraint, so it 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 three-parameter export tool with zero schema description coverage and no output schema, the description leaves key gaps: what the call returns (download URL, token, job id), whether the link expires, and how template/list interact. The caller can guess the high-level intent but not the mechanics.

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% and two of three parameters are enums (kind, template) whose allowed values and effects are invisible in the description. 'Owned records' hints weakly at the list parameter, but nothing explains what template does (column mapping for the named CRM?) or why list scopes the export.

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 names a specific verb+resource ('Prepare an authenticated CSV download request for owned records'), so an agent understands the outcome without opening the schema. It does not differentiate from siblings such as preview_records, owned_records, or coverage, nor does it say what 'kind' selects (agents vs brokerages), leaving some overlap ambiguity.

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?

'No credits spent' implies a contrast with the credit-consuming unlock_records sibling, and 'do not include your API key in a URL' is a usable operational caveat. However, there is no explicit 'use this when / use X instead' guidance and no stated prerequisites for choosing between this and preview_records.

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