notification_email

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false and destructiveHint=false, so the safety profile is covered; the description adds the genuinely useful context that this is a two-phase email-confirmation flow where the code arrives out-of-band and must be supplied by the user. The token handoff between verify_code and the later actions is disclosed. What unsubscribe does to existing notification preferences, and any rate limits on request_code, are not stated.

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?

Front-loaded with the purpose in the first sentence, followed by the confirmation requirement and a compact action-to-parameter map. Every sentence earns its place and nothing is padded. The action enumeration is slightly dense but remains scannable.

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 five-parameter, action-dispatch tool with no output schema, the description covers the full user-facing flow, the out-of-band nature of the code, and the token usage — enough to invoke it correctly. Missing are error behavior (expired/invalid code), whether request_code can be repeated, and what a successful set_subscription returns.

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 only 40% (only 'code' and 'token' are documented), so the description has to compensate — and it does, mapping every action to its required inputs: request_code(email), verify_code(email + code), set_subscription(token + subscribed), unsubscribe(token). That assigns meaning to the otherwise undocumented email, subscribed and action fields. It does not add format details for email or subscribed beyond what the enum/boolean type implies.

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?

States a specific verb and resource ('Manage an email address subscription to Convocore notification emails') and then enumerates the four concrete actions, so an agent knows exactly what the tool covers. It never references a sibling tool, but the notification-email scope is narrow enough that it is distinguishable from email_channel_read/write by subject matter alone.

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 action list encodes the required workflow order — request_code, then verify_code to obtain a token, then set_subscription or unsubscribe with that token — which is real operational guidance, not just a field listing. The line 'You cannot read the code yourself — ask the user for it' is an explicit, actionable constraint on how to run the flow. It stops short of saying when not to use the tool or how it relates to sibling email tools.

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