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

Annotations provide readOnlyHint=false and destructiveHint=false, meaning this is a write operation that is not destructive. The description adds that it only records invites and does not send anything, and that each returned link can be included in an email or message. This clarifies that no external communication is triggered, which is valuable beyond the annotations.

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?

The description is two sentences, front-loaded with the core action and result. It efficiently covers the non-sending behavior and the lang parameter without wasted words. Every sentence adds value.

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?

Given that an output schema exists, the description does not need to explain return values. It covers the key behavioral aspects relevant to an agent: what it records, what it returns, that it does not send, and how lang maps to the user's context. Nothing essential is missing for a correct invocation.

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%, so the baseline is 3. The description adds a small amount of context for 'lang' (records the language of the invite) and 'recipients' (colleagues the user chose), but largely restates the schema descriptions. It does not significantly enhance parameter meaning beyond what the schema already provides.

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?

The description states a specific action ('Records referral invites'), the resource ('colleagues a user chose to invite'), and the outcome ('returns a unique referral link per person'). It also clarifies the purpose (to later see who installed or activated LMCP), distinguishing it from email-sending or listing tools. The verb and resource are unambiguous.

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 description explicitly says 'It does not send anything itself', which sets a clear boundary against send-type tools (e.g., send_email). However, it does not name an alternative tool like list_referral_candidates or send_email, nor does it describe when to choose this over other referral-related tools. The exclusion is stated, but explicit alternatives are missing.

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