Get notification preferences

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 useful context: which channels it covers (email, Slack, webhook) and explicitly excludes addresses/URLs ('Returns no addresses or URLs'), setting expectations about the response. However, it doesn't state whether all three channels are always present or what happens with disabled channels.

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 sentences, zero wasted words. The first sentence states purpose and scope; the second sentence preempts a common confusion (addresses/URLs) and directs to the correct sibling tool. Excellent front-loading and economy.

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 simple read tool with one well-documented parameter, strong annotations, and no output schema, the description covers what's needed. It explains return semantics (channel toggles), scoping (per-project), and distinguishes from the likely-confused sibling. The only minor gap is not describing the exact return structure/format of the channel switches, but with no output schema requirement, this is adequate.

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% and the project_id parameter is well documented in the schema ('Identifier of the bisibility project to operate on; list_projects returns valid project ids'). The description adds the project-scoping context but doesn't need to explain the single parameter further since the schema fully covers it. Baseline 3 is appropriate.

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?

Clear verb+resource: 'get which channels (email, Slack, webhook) are turned on for the project.' The description explicitly states what is returned (channel toggles) and distinguishes from the sibling get_notification_preferences vs update_notification_preferences (read vs write) and list_webhooks (addresses/URLs vs toggles). The 'Returns no addresses or URLs' phrasing actively differentiates it from list_webhooks.

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 scoping context ('for the project') and explicitly points to list_webhooks as the alternative for destination details ('use list_webhooks for where notifications are sent'). It doesn't explicitly say when-not-to-use, but the sibling differentiation gives practical guidance. Could mention that this is a read complement to update_notification_preferences, but that's implied.

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