List recent card data changes (welcome bonus updates, fee changes, multiplier edits). Useful for "what changed recently?" queries.
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | Look back this many days (default 30). | |
| limit | No | Max results (default 50). | |
| card_id | No | Filter to changes for one card. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description characterizes the tool as a read-only listing operation ('List recent card data changes'), which directly contradicts the annotation destructiveHint: true. Although it aligns with readOnlyHint: true, the conflicting destructiveHint creates an irreconcilable contradiction that the description does not resolve or acknowledge.
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 with zero redundancy. The core action and resource are front-loaded, examples clarify scope, and the usage prompt is concise. Every word earns its place.
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 the contradictory annotations (readOnlyHint true vs destructiveHint true), the description is not fully contextually complete because it leaves the destructive annotation unaddressed, potentially confusing an agent. The description itself is clear for a simple list tool, but the surrounding annotation conflict reduces overall completeness.
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%, with each parameter (days, limit, card_id) already documented in the input schema. The description adds no parameter-level detail beyond the schema, so the baseline score of 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?
The description uses a specific verb and resource: 'List recent card data changes,' and provides concrete examples (welcome bonus updates, fee changes, multiplier edits). This clearly distinguishes it from sibling tools like cards_list_cards and cards_get_card, which focus on the cards themselves rather than their change history.
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 frames the tool's intended use case: 'Useful for "what changed recently?" queries.' This gives clear context for when to invoke it. It does not name exclusions or alternatives, but for a simple read-only listing tool, the context is sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several tools are near-duplicates (log_lounge_visit vs lounge_mark_lounge_visited, delete_lounge_visit vs lounge_delete_visit, audit_hotel_folio vs audit_marriott_folio) and the award-chart tools (get_pricing, get_program_rates, get_partner_award_options, get_program_partner_chart) have unclear boundaries. The three discover_more_flight_tools variants and overlapping lounge/portfolio listers compound the ambiguity, so an agent can easily pick the wrong one.
Most tools use snake_case verb_noun names and many have consistent prefixes (cards_, lounge_, fs_, sw_), but prefixes are applied inconsistently: log_lounge_visit/delete_lounge_visit sit outside the lounge_ prefix while equivalent lounge_* tools exist, and fs_search_flight references a non-existent search_flight. The broad get_/list_/search_ verbs are predictable, but the mixed domain-prefix style and duplicate concepts hurt coherence.
136 tools is far beyond a well-scoped server and bundles at least eight distinct domains (award search, cards, hotels, lounges, seatmaps, wifi, Viator, feedback). Many tools could be split into separate MCPs without loss of coherence, and the sheer count makes selection and prompt overhead prohibitive.
The core award-travel domain is well covered: bookings, hotels, points balances, statuses, vouchers, monitors, trips, and cards all have lifecycle CRUD, plus search and reference tools. Minor gaps exist (e.g. no true delete for standing orders, no single get for route monitors, and the Viator pair is an isolated mini-domain), but agents can generally complete workflows without dead ends.
