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

Annotations only declare the mutation/open-world profile; the description adds the substantive behavior: a pairing_code is returned, the human gets at most one email, they must open its page and confirm, and the response is identical whether or not an email is sent (enumeration-safety disclosure). It also warns the code must be shown only in chat, and that the credit still requires human approval to spend.

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?

A single dense paragraph, front-loaded with the precondition and the offer, then the mechanics and constraints. Nearly every sentence carries information, though the 'Show that code ... and nowhere else' instruction sits awkwardly mid-flow.

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?

With no output schema, the description supplies the return value (pairing_code) and the full human-side confirmation loop, plus rate/offer limits. An agent has everything needed to call it and explain the result to its human.

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 the schema already documents 'email' and 'passport_token'. The description reinforces that the email belongs to the human but adds nothing new about the optional passport_token fallback; baseline 3 applies when the schema does the work.

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: ask for a free $5 starter credit for the human tied to an ownerless passport. The scope phrase 'For a passport without an owner' plus the credit amount distinguishes it from siblings like buy, top_up, and starter_status, though those siblings are never named.

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 preconditions ('For a passport without an owner'), limits ('once per inbox, while the offer lasts'), and a downstream constraint ('Buying with the credit still needs your human's yes, like any purchase'). It does not explicitly route to alternatives such as starter_status for checking state or top_up for payment, leaving that to inference.

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