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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so safety is covered. The description adds a genuinely useful behavioral constraint not present in structured data — only verified subscribers are returned — which changes how an agent should interpret a miss. It still says nothing about not-found behavior (empty result vs error) for an unverified or nonexistent code.

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 compact sentences with the core definition front-loaded and the verification caveat immediately after it. The trailing GET path is low-value for an agent deciding whether to call the tool, but it is a single clause and does map the tool to its API endpoint.

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 two-parameter read lookup with full schema coverage, annotations, and no output schema, the description conveys what is returned (the owning subscriber) and the key filtering rule. The only meaningful gap is the response when no verified subscriber matches, which an agent needs in order to handle the result.

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 coverage is 100%, so both parameters are fully documented, including the uuid format and the mwr interpretation of referral_code. The description's parenthetical about mwr restates what the schema already says and adds no syntax, format, or validation detail; baseline 3 applies when the schema carries the load.

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 concrete verb and resource (find the subscriber who owns a referral code) and disambiguates the lookup key by explaining that the referral code is the mwr value in a referral link. This distinguishes it in practice from get_subscriber_by_email and search_subscribers_by_name, though no sibling is named explicitly.

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?

Usage is implied by the lookup key rather than stated: an agent must infer that this is the tool to use when it has a referral link's mwr value. The one real guidance signal is the caveat "Only verified subscribers are found," which tells the agent when this tool will fail to locate someone, but there is no explicit routing against get_subscriber or get_subscriber_by_email.

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