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

Annotations already carry the safety profile (destructive, idempotent, not read-only), and the description adds real substance beyond them: push-propagation timing, per-device voiding, changeMessage lock-screen behavior, and the expiration window. It stops short of saying what happens to an already-voided pass or whether a failed push is retried, but the key destructive consequences are disclosed.

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?

Dense and front-loaded — purpose and refresh behavior come first, then input contract, then edge cases, then returns. Nearly every sentence earns its place, though the wrapping around 'the required contact_email and x402_ready' reads awkwardly mid-sentence and the return-value paragraph is longer than strictly necessary.

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 43-parameter mutation tool with no output schema, coverage of lifecycle (updatable_until), destruction (voided), async propagation, and return fields including the notified_devices caveat is strong. The gap is per-parameter meaning: an agent must open create_wallet_pass's schema to interpret fields like style, semantic_layout, transit_type, or featured_actions.

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?

With 43 parameters at 0% schema description coverage, the description does the heavy lifting on the most error-prone semantics: replace-not-merge ('a fields list replaces the whole list, so resend unchanged fields too'), omit-to-preserve, and empty-value clearing. The remaining ~35 optional parameters are handled by reference ('any of create_wallet_pass's parameters, with the same meanings'), which is efficient but forces a second lookup, and the 'unknown' enum value on x402_ready is never explained.

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?

Opens with a specific verb+resource ('Change a pass') and immediately scopes it to passes created with create_wallet_pass(updatable=True), naming the sibling tool. The downstream effect ('every iPhone that added it refreshes') further distinguishes it from a mere local edit.

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?

Explicitly states prerequisites (edit_token and serial_number from creation), the hard boundary ('Only works until the pass's updatable_until time'), and the cancellation path ('set voided=True'). The clearing conventions ('Clear a text value with "" and a list with []') are the kind of when-to-do-what guidance an agent would otherwise get wrong.

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