Notification Targets

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

Annotations indicate destructiveHint=true and readOnlyHint=false, but the description adds the 'requires elevated' permission note for create/delete/test, which is beyond annotations and useful. It also implies list/get are read-only by labeling them 'query targets'. However, it doesn't detail the consequences of delete (permanence), or what test does (sends a test notification), which would improve transparency.

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 a single, compact sentence that front-loads the core action groups and the elevated permission note. It is efficient and not verbose, earning a high score for conciseness, though it could be slightly more structured (e.g., bullet points) without adding length.

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 15 parameters and 5 possible actions, the description is too brief to be considered complete. It does not explain which parameters are required for each action or how target_type (smtp/gotify/sendmail) alters parameter usage. There is no output schema, so the description alone must guide the agent, but it leaves too much to inference. It is not self-contained for correct invocation.

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?

Although the schema has 100% description coverage, the description itself does not map parameters to specific actions or target types. The schema's 'action' description is misleading ('List all notification targets' only covers the 'list' action, not all five). The main description does not clarify which parameters apply to which action (e.g., server/port only for smtp, token for gotify). The agent would need to infer usage, which is a significant gap.

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 resource (notification targets) and the primary verb (manage), and enumerates the specific actions (list, get, create, delete, test). This distinguishes it from other Proxmox tools which target different resources. However, it could be more explicit about the types of targets (smtp, gotify, sendmail) and that this is specific to notification configuration, which is implied but not stated.

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 separates query actions (list/get) from management actions (create/delete/test) and notes elevated permissions for the latter, but it provides no guidance on when to choose this tool over other tools (e.g., proxmox_user, proxmox_group, etc.). It lacks explicit alternatives or exclusions. The usage context is only internal to the tool's actions, not comparative.

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