Aedifion MCP Server

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

With no annotations provided, the description carries the full disclosure burden but fails to explain activation behavior, side effects (e.g., immediate alert evaluation), or mutation characteristics. It does not clarify what happens when multiple thresholds are defined, if null thresholds disable that severity level, or whether alerts are active immediately upon creation.

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 structure is efficient with a clear single-sentence purpose followed by a structured parameter list. Each sentence earns its place with no redundant prose. The Args format is appropriate given the complete lack of schema descriptions, though grouping related parameters (thresholds vs notifications) would improve scannability.

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?

While the description covers all 9 parameters and the tool has an output schema (reducing the need for return value description), it lacks important contextual details for a monitoring/alerting tool: threshold precedence logic, notification delivery guarantees, and the interaction between optional null defaults and alert behavior. Adequate but incomplete given the domain complexity.

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?

Given 0% schema description coverage, the Args block provides crucial semantic context: 'datapoint to monitor' explains the resource relationship, severity levels (info/warn/crit) add domain meaning, and 'evaluation period in seconds' clarifies the temporal aspect. Minor deduction for not explaining null-default behavior or whether at least one notification channel is required.

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 specific verb (Create) and resource (threshold-based alert) with the 'new' qualifier distinguishing it from the sibling update_threshold_alert. However, it does not explicitly differentiate from other alert management tools like delete_alert or enable_alert, nor does it reference when to prefer this over updating existing alerts.

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 no guidance on when to use this tool versus alternatives (e.g., updating existing alerts with update_threshold_alert), nor does it mention prerequisites like project existence or datapoint availability. There are no warnings about required vs optional notification channels.

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