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

Adds real behavior beyond the annotations: a confirmation link is emailed, and flows can only email the address after the person confirms, meaning the created recipient starts in a pending state. It also discloses the owner/admin permission requirement, which the annotations (readOnly=false, idempotent=true, destructive=false, openWorld=true) do not convey.

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?

Three tight sentences, zero filler: purpose first, then the confirmation mechanic, then the permission gate. Nothing is repeated from the title or schema and every sentence carries information.

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 2-parameter tool with no output schema, the description supplies the crucial nuance an agent needs: the recipient is not immediately usable and must confirm. It omits any hint about the return shape or what identifier comes back, and never mentions the optional label, but nothing essential to correct invocation is missing.

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% with both 'email' and 'label' documented in the schema, so the description is not required to carry parameter meaning. It adds no format or constraint detail beyond the schema (e.g., it never mentions that a human-readable label may be supplied), so the baseline of 3 applies.

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?

Specific verb ('Add') plus a precisely scoped resource ('an email address outside the team that flows may notify'), which separates it from neuron_remove_notify_recipient and neuron_list_notify_recipients and from internal team-member tools like neuron_invite_member. The scope qualifier 'outside the team' is the key disambiguator and is stated up front.

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?

Gives clear context for use (you want flows to notify someone outside the team) and states the prerequisite 'Owners and admins only', which is effectively an authorization condition. It does not explicitly name the remove/list siblings as the alternatives, so it stops short of a full when/when-not rubric.

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