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

Adds substantive behavior the annotations cannot express: the tool may trigger a double opt-in confirmation email, making the write have an outbound side effect. It also discloses that a duplicate email returns a conflict error, which corroborates the non-idempotent annotation. Auth requirements and rate limits remain undisclosed.

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 with zero filler, led by the uppercase write/side-effect warning so the agent sees the risk before anything else. Every sentence carries distinct 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?

No output schema exists, yet the description covers the key things an agent needs before writing: side effects, consent precondition, and the duplicate-error path. It is slightly thin on what the call returns and whether existing subscriber fields get overwritten versus merged.

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?

The description supplies no parameter-level meaning at all; it only expresses scope ('one subscriber'). With 60% schema coverage, the non-obvious fields (first_name, last_name, custom_fields with its cross-reference to mailblaze_list_list_fields) are covered by the schema itself, so 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?

States a specific verb and resource ('add one subscriber to a mailing list') and scopes it to a single record, which implicitly separates it from mailblaze_add_subscribers_bulk. It does not name the bulk sibling or the lookup tool explicitly, so differentiation is inferable rather than 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?

Provides a real precondition ('Only add people who agreed to receive your email') and explains the duplicate outcome, but never routes the agent to alternatives such as mailblaze_find_subscriber_by_email to pre-check existence or mailblaze_add_subscribers_bulk for multiple people. Usage is implied rather than directed.

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