Cherishly is a reverent memorial keepsake generator that creates high-resolution, shareable tribute cards honoring loved ones. Backing the Cherishly mobile apps on iOS, Android, and www.cherishlyapp.com , this MCP server empowers AI assistants to design beautiful keepsakes with gold foil typography, custom photo medallions, and interfaith honorifics in seconds.
Scored across 2 tools
The two tools differ only by singular/plural naming and batch semantics; the descriptions clarify single vs. batch (max 3), but the near-identical names make misselection easy on a typo or fuzzy match.
Both names follow a consistent snake_case verb_noun pattern (generate_tribute_card / generate_tribute_cards). The singular/plural distinction is a recognized convention, though it is a fragile differentiator.
Only 2 tools for a card-generation service is thin; the batch variant could plausibly be folded into the single tool via a count parameter, leaving little reason for two separate endpoints.
Core generation (single and batch) is covered, but there is no way to list themes, retrieve previously generated cards, or check generation status/history, leaving lifecycle gaps for repeat use.
Generate an elegant, high-resolution Cherishly keepsake tribute card from a person's name, dates, photo, and message. Returns full-res signed download URLs (PNG & JPEG) and an inline preview image. Free generation is subject to fair-use limits and daily service capacity resetting at 00:00 UTC. Only the person's name is required; ask only for essential missing details. Defaults to vibrant 'sage' theme (forest emerald with polished gold foil) and '1:1' square social media size.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Full name of the person being honored (required, max 80 chars, e.g. 'Jane Doe', 'Sheikh Abdul Rahman'). | |
| dates | No | Lifespan or commemorative dates (optional, max 60 chars, e.g. '1945 – 2021', '1365 – 1442 AH'). Leave blank if unknown. | |
| ratio | No | Aspect ratio: '1:1' (RECOMMENDED DEFAULT: Square 1080×1080 for Instagram feed, WhatsApp profile/status, Twitter/X, Facebook), '4:5' (Portrait 1080×1350 for Instagram feed), '2:3' (Story 1080×1620 tall commemorative print). | 1:1 |
| theme | No | Visual theme palette: 'sage' (RECOMMENDED DEFAULT: rich deep forest emerald with polished gold foil), 'midnight' (obsidian black with platinum silver), 'ocean' (deep navy with wave silver), 'burgundy' (imperial wine with royal gold), 'sunset' (warm terracotta with radiant bronze), 'blossom' (dusty rosewood with blush accents), 'geometric' (ornate Islamic emerald with arabesque gold), 'ivory' (light cream paper with champagne gold). | sage |
| message | No | Remembrance quote, epitaph, or loving words (optional, max 500 chars). Leave blank if not provided. | |
| photoUrl | No | Secure HTTPS URL pointing to the person’s photograph (JPEG, PNG, or WebP). Embedded respectfully into a circular gold medallion without face distortion. | |
| honorific | No | Optional honorific or prayer abbreviation (e.g. 'RA', 'ﷺ', 'PBUH', 'Rahimahullah', 'Late'). | |
| photoBase64 | No | Base64-encoded image data or data URI (JPEG, PNG, or WebP, max 3.5MB). Embedded respectfully into a circular gold medallion without face distortion. | |
| relationship | No | Relationship to user (optional, e.g. Parent, Grandparent, Sibling, Child, Spouse, Friend, Teacher, Mentor, Other). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does well: it discloses the return shape (full-res signed PNG & JPEG download URLs plus inline preview), free-tier fair-use limits, and a daily capacity reset at 00:00 UTC. It omits other behavioral details an agent might want, such as signed-URL expiry, authentication prerequisites, and failure behavior when capacity is exhausted.
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?
Four sentences, each carrying distinct information: output shape first, then limits, then required input, then defaults. The closing defaults sentence partially duplicates schema defaults, keeping it just short of a 5.
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 9-parameter generation tool with full schema coverage and no output schema, the description covers output format, limits, required inputs, and defaults well. It leaves minor gaps around choosing between the two photo inputs and the singular-vs-plural sibling distinction.
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 every one of the 9 parameters is already documented in the schema, including enum values and defaults. The description restates the 'sage' theme and '1:1' ratio defaults but adds no guidance on, for example, when to prefer photoUrl over photoBase64, so the baseline 3 applies.
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 (Generate) and a well-defined resource (Cherishly keepsake tribute card) built from name, dates, photo and message, which is far more than a restatement of the name. It does not, however, address the sibling tool generate_tribute_cards (plural), so an agent has no in-description basis to choose between the singular and plural variants.
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 gives useful calling guidance ('Only the person's name is required; ask only for essential missing details') and states the fair-use/capacity conditions under which free generation is available. It never says when NOT to use this tool or routes the agent to the plural sibling, so usage is implied rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate a collection of Cherishly keepsake tribute cards (batch max 3 cards per call). Free generation is subject to fair-use limits and daily service capacity resetting at 00:00 UTC. Returns high-resolution download URLs and previews.
| Name | Required | Description | Default |
|---|---|---|---|
| ratio | No | Aspect ratio for all cards in the collection (default: '1:1'). | 1:1 |
| tributes | Yes | Array of tribute card specifications (1 to 3 tributes). | |
| defaultTheme | No | Default theme for the collection (default: 'sage'). | sage |
| collectionTitle | No | Title for the memorial collection (max 80 chars, e.g. "Smith Family Memorial Keepsakes"). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden and does reasonably well: it discloses a hard batch cap (3), fair-use limits, a daily capacity reset at 00:00 UTC, and the return artifacts (high-resolution download URLs and previews). It stops short of quantifying the fair-use limit or describing failure modes when the cap/capacity is exceeded.
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?
Three sentences with the purpose front-loaded, followed by operational constraints and return contents; no filler. Slightly denser than ideal by packing limits and returns into one closing sentence, but nothing is wasted.
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?
No output schema exists, and the description compensates by naming the return artifacts (download URLs and previews). Combined with the batch cap and capacity reset disclosure, an agent has what it needs to call the tool; only explicit routing versus the sibling tool is absent.
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 schema already documents ratio, defaultTheme, collectionTitle, and the nested tribute fields. The description only restates the batch size, which the schema itself specifies as '1 to 3 tributes,' adding no syntax or constraint detail beyond structured fields. Baseline 3 applies.
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 verb and resource ('Generate a collection of Cherishly keepsake tribute cards') and flags the batch nature via 'collection' and 'max 3 cards per call,' which implicitly distinguishes it from the singular sibling generate_tribute_card. It never names the sibling or states the single-card case explicitly, so the differentiator must be inferred.
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 context is implied by 'collection'/'batch max 3' versus the singular sibling, plus the free-tier fair-use note, but there is no explicit 'use this instead of generate_tribute_card when...' statement or any when-not guidance. The agent can infer batch-vs-single but is not told outright.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
generate_tribute_cardgenerate_tribute_cards
Add one secure layer between your agents and this server.