Update notification preferences

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

Annotations only declare readOnlyHint=false, openWorldHint=false, destructiveHint=false, which tells the agent this is a write operation but not destructive. The description clarifies it's a toggling operation and doesn't create/modify webhook endpoints, but doesn't disclose behavior details like idempotency semantics, partial vs full replace of unspecified channels, or confirmation behavior. For a write tool with minimal annotations, some additional behavioral context (e.g., what happens to unlisted channels) would help.

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 fluff. Each sentence earns its place: the first states the core function, the second clarifies scope boundaries and names alternatives. Highly front-loaded with the essential purpose in the first sentence.

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 moderately complex tool (12 boolean parameters across semantic categories) with no output schema and only 8% schema coverage. The description clarifies the webhook boundary well but does not explain the semantic grouping of parameters (alert vs check vs import vs invite), which is the main cognitive burden for the agent. Given the complexity and low coverage, more description would be warranted.

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 8% (only project_id has a description), with 12 parameters total. The description names the three channels (email, Slack, webhook) but the actual parameter list uses more granular naming (alert_email, check_email, import_email, invite_email, and corresponding _in_app variants). The description does not explain what alert/check/import/invite categories mean or how boolean false interacts with unspecified channels. Given very low coverage, the description should compensate more, so baseline 3 is generous.

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?

Clearly states the tool's purpose: turning notification channels (email, Slack, webhook) on/off. The verb 'update' plus the resource 'notification preferences' and the specific behavior (channel switches) distinguish it from sibling tools like create_webhook/update_webhook.

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?

Explicitly states what it does NOT do ('does not create or change webhook endpoints') and directs the agent to the alternative tools (create_webhook/update_webhook). This is exemplary when/not/alternatives guidance, especially valuable given the large sibling list.

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