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

The description goes beyond the annotations by disclosing that creation also 'Auto-generates a template workflow and lead list' and by clarifying the distinct roles of accountIds ('observe the feed') and actAccountIds ('act on signals'). This is valuable side-effect context that annotations alone do not provide. It does not fully explain the implications of responseMode auto_send, but the main behavioral surprises are surfaced.

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 front-loaded with the core purpose and then adds necessary detail about target variants and account roles. Every sentence contributes meaning; the examples are verbose but justified by the complex polymorphic target schema. It could be slightly trimmed, but it remains efficient and well organized.

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?

This is a complex creation tool with 11 parameters, nested objects, no output schema, and no parameter descriptions in the schema. The description covers the target structure and core account semantics well, but leaves required fields like type, targetName, and responseMode unexplained. The responseMode enum (auto_send vs review_first) is especially important for understanding autonomous behavior and should have been described. The auto-generated workflow/lead list side effect is mentioned but not elaborated on.

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%, so the description must compensate. It does explain the target object's three shapes with concrete examples, and it clarifies accountIds vs actAccountIds. However, several required parameters — type, targetName, responseMode, and optional but important ones like silenceHours, publicReplyConfig, and followUpDelaysHours — are not given any semantic explanation beyond their names and enum values.

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 opens with a specific verb and resource: 'Create a new signal agent', and specifies exactly what it monitors (LinkedIn profile, company feed, group, or post) plus the side effects (auto-generates template workflow and lead list). It distinguishes this from sibling watch/agent creation tools by describing a broader automation agent rather than a simple watch, and the target variants clarify scope.

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 usage context: when you want to create a signal agent that watches LinkedIn sources and acts on engagements. It also tells the user to call campaignstack_list_accounts to find account IDs. However, it does not explicitly contrast with similar siblings like campaignstack_create_signal_watch, campaignstack_create_connection_watch_agent, or campaignstack_create_competitor_watch, so an agent gets no explicit when-not-to-use guidance.

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