AI-generate email subject lines and body content for a campaign. Describe the goal, audience, and tone.
| Name | Required | Description | Default |
|---|---|---|---|
| tone | No | e.g. professional, friendly, urgent, casual | |
| prompt | Yes | Describe the campaign goal, audience, and key message | |
| num_variants | No | Number of subject/body variants to generate | |
| campaign_type | No | myconvo (personal) or nextgen (bulk) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds that it's AI-generated but doesn't disclose return format or side effects, which is acceptable given the annotation coverage.
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 single sentence is front-loaded and information-dense. Every word contributes to understanding the tool's function and usage, with no wasted content.
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 4-parameter schema with full descriptions and annotations, the description adequately covers the tool's purpose and basic usage. It could mention output variants or return structure, but those are implicitly handled by the schema and purpose.
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 the schema documents all parameters. The description reinforces the prompt's purpose but doesn't add meaningful new semantics beyond what the schema already provides.
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 AI-generates email subject lines and body content for a campaign, using a specific verb and resource. This distinguishes it from sibling tools like create_campaign or run_ai_report, which have different purposes.
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 clear context by instructing the user to describe the goal, audience, and tone, implying when to use it. However, it doesn't explicitly mention alternatives or exclusions, so it doesn't earn a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several tools occupy nearly identical roles (create_contact/add_contacts/save_contacts_to_crm/upload_contacts; add_companies/create_company; search_contacts/search_crm_contacts/find_contacts_at_companies), and the names don't clearly reveal whether they operate on saved or prospected data. Although the descriptions clarify some boundaries, an agent would frequently need to read many descriptions carefully to avoid mis-selection.
Most tools follow a snake_case verb_noun pattern such as list_campaigns, create_deal, and update_contact. Minor deviations like company_intelligence, get_icp, load_more_contacts, and the inconsistent use of add_/create_/upload_/save_ for similar creation actions keep it from being fully consistent.
51 tools is far beyond the well-scoped range and exceeds the 50+ extreme threshold. Even for a broad CRM/prospecting/marketing platform, exposing this many tools at once makes agent selection costly and unwieldy.
Contact and company creation/read/update are covered, but delete is absent across the board, and campaigns can be drafted, listed, and measured but not edited, activated, paused, or deleted. Deals, forms, and landing pages also lack update/delete lifecycle actions, creating meaningful dead ends for common CRM workflows.
