Render chart images from JSON configs via a simple HTTP API. Six themes, ten marks, PNG/SVG output. No client-side JavaScript, no installs – just a URL that returns an image. MCP tools include render, validate, list themes, and browse examples.
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Average 4.5/5 across 13 of 13 tools scored.
Most tools have clearly distinct purposes, but get_chart and get_chart_config are both retrieval-by-id operations that require careful reading to distinguish metadata/URLs from config. Additionally, get_preview_state is somewhat cryptic despite its description, but overall overlap is minimal.
All 13 tool names follow a consistent verb_noun pattern in lowercase snake_case (e.g., delete_chart, get_chart_config, list_themes). There are no deviations or mixed conventions, making the naming predictable and coherent.
With 13 tools, the server is well-scoped for a charting service. Each tool serves a distinct role in the workflow (reference, validation, CRUD, rendering), and the count is neither sparse nor overwhelming, fitting within the ideal 3-15 range.
The tool surface covers the full chart lifecycle: create (save_chart), read (get_chart, get_chart_config, list_charts), update (update_chart, rename_chart), and delete (delete_chart). It also includes validation, rendering, reference data (examples, marks, themes), and preview state restoration, addressing practical needs. Minor gaps like explicit draft management are indirectly handled through update_chart's safeguards.
delete_chartDelete chartAUse this when the user explicitly wants to permanently delete one saved chart. Deletion cannot be undone, and retrying an already completed deletion succeeds; requires authentication.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Opaque 32-character saved-chart id |
| Name | Required | Description |
|---|---|---|
| deleted | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate destructive and idempotent behavior, but the description adds valuable context: 'Deletion cannot be undone' elaborates on the destructive hint, 'retrying an already completed deletion succeeds' clarifies idempotency, and 'requires authentication' discloses a requirement not present in the annotations. This goes beyond what structured data provides.
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 a single, tightly packed sentence that front-loads the usage context and then includes irreversibility, idempotency, and authentication. Every clause earns its place; there is no redundancy or padding.
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 simple single-parameter destructive tool with full annotations and an output schema, the description covers all necessary aspects: when to use it, side effects, retry behavior, and authentication. The agent has enough information to select and invoke the tool correctly without needing external details.
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?
The description does not mention parameters, but the schema fully covers the single 'id' parameter with a description ('Opaque 32-character saved-chart id') and pattern. With 100% schema description coverage, the baseline of 3 applies; the description adds no additional parameter-level meaning.
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 clearly states the tool's purpose: 'permanently delete one saved chart.' It uses a specific verb and resource, distinguishing it from sibling tools like rename_chart or update_chart. The addition of idempotency ('retrying an already completed deletion succeeds') further clarifies the exact behavior.
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 'Use this when the user explicitly wants to permanently delete one saved chart,' providing clear usage context. It does not name alternative tools or explicitly state when not to use it, but the conditional phrasing implies this is only for explicit deletion requests.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_chartGet chartAUse this when the user identifies a saved chart by id and wants to view it or retrieve its metadata and URLs. Displays the published chart when available and does not return its config; requires authentication.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Opaque 32-character saved-chart id |
| Name | Required | Description |
|---|---|---|
| id | Yes | Opaque 32-character saved-chart id |
| view | Yes | |
| title | Yes | Saved chart title |
| source | Yes | Chart origin; an open set of string values |
| editUrl | Yes | |
| embedUrl | Yes | Interactive-embed URL |
| imageUrl | Yes | Rendered-image URL |
| configUrl | Yes | Owner-only chart-config endpoint |
| createdAt | Yes | ISO-8601 creation timestamp |
| manageUrl | Yes | |
| sizeBytes | Yes | Compressed size of the stored published config, excluding drafts; 0 means no published config has been stored yet |
| updatedAt | Yes | ISO-8601 last-update timestamp |
| publishedAt | Yes | ISO-8601 publish timestamp, or null when public URLs are dark |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the description focuses on additional context: 'Displays the published chart when available', 'does not return its config', and 'requires authentication'. These add value beyond annotations, though error handling is not mentioned.
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?
Two sentences with no redundant information. Every sentence adds value: use case, behavior (published chart, no config), and auth requirement. Extremely efficient.
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 simple single-parameter input schema, existing output schema, and annotations that cover safety, the description is complete. It explains what the tool returns (metadata and URLs) and what it doesn't (config), and mentions the authentication requirement.
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% for the single parameter 'id', which is fully described with type, pattern, and description. The description adds no further parameter information, so 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 specifies a verb ('view', 'retrieve') and resource ('saved chart by id'), and it clearly distinguishes from sibling tools by stating it does not return the config, which differentiates it from get_chart_config.
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 when to use ('when the user identifies a saved chart by id and wants to view it or retrieve metadata and URLs') and implicitly excludes cases needing config or without an id. Could be improved by adding an explicit 'do not use if...' statement, but it is still clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_chart_configGet chart configAUse this when the user identifies a saved chart by id and needs its complete published Szum config for inspection or reuse. Does not return a newer editor draft; requires authentication.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Opaque 32-character saved-chart id |
| Name | Required | Description |
|---|---|---|
| x | No | |
| y | No | |
| data | No | |
| color | No | |
| marks | Yes | |
| scale | No | |
| theme | No | |
| title | No | |
| width | No | |
| footer | No | Caption below the chart (a source line, methodology note, date). URLs, bare domains, and [label](url) links in it are auto-detected and rendered as inline links on every surface. |
| format | Yes | |
| height | No | |
| locale | No | Locale identifier accepted by JavaScript Intl and associated with the chart content, such as en, pl, or zh-Hant. |
| margin | No | |
| version | Yes | |
| subtitle | No | |
| plotWidth | No | |
| plotHeight | No | |
| attribution | No | Show a small "Made with Szum" credit in the bottom-right. Always on for free and keyless renders; Creator and Pro omit it by default and set true to opt in. |
| headerAlign | No | |
| themeOverrides | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only and non-destructive hints, and the description adds valuable context: authentication is required, and the tool returns only the published config, not the editor draft. This goes beyond the annotations by disclosing an access prerequisite and a key behavioral limitation.
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 primary usage directive. Every sentence earns its place: first gives the purpose and condition, second clarifies limitations and auth. No wasted words.
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 an output schema present and a single fully-documented parameter, the description covers the essential context: what the tool does, when to use it, what it doesn't return, and an important prerequisite. It is sufficiently complete for an agent to select and invoke the tool correctly.
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?
The schema fully documents the single parameter `id` with a pattern and description (100% coverage), so the description doesn't need to add param details. The mention of 'by id' aligns with the schema but adds no new meaning. Baseline of 3 is appropriate given high schema coverage.
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 clearly states the tool retrieves a saved chart's complete published config by id for inspection or reuse. It uses a specific verb (get) and resource (chart config), and distinguishes itself from sibling tools like get_chart by specifying the published Szum config rather than an editor draft.
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 'Use this when...' and delineates the scope (saved chart by id, published config). It also provides a critical when-not by stating it does not return a newer editor draft, implying this tool is for published configs only. This gives clear usage context without naming alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_examplesGet example chartsAUse this when the model needs current, ready-to-use Szum chart configs or preferred semantic patterns. Optionally filters examples by mark type.
| Name | Required | Description | Default |
|---|---|---|---|
| mark_type | No | Filter examples by mark type |
| Name | Required | Description |
|---|---|---|
| examples | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnlyHint=true and destructiveHint=false, covering safety expectations. The description adds minimal extra context (e.g., 'current' and 'preferred semantic patterns') but does not elaborate on return behavior or edge cases. This matches the baseline for a read-only tool with 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 concise sentences, front-loaded with the usage trigger ('Use this when...'), and contains no wasted words. Every clause adds information about purpose or filtering.
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?
The tool is simple (one optional parameter, read-only) and has an output schema, so the description need not explain return values. It fully covers when to use the tool and the optional filter behavior, making it complete for the given complexity.
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?
The schema fully documents the only parameter (mark_type) with an enum and description. The description's phrase 'Optionally filters examples by mark type' repeats what the schema already conveys, adding no new semantic detail. Schema coverage is 100%, so the baseline score of 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 clearly states the tool's purpose: to retrieve current, ready-to-use Szum chart configs and preferred semantic patterns. It uses a specific verb ('get') and resource ('examples'), and the optional mark-type filter distinguishes it from sibling tools like get_chart or list_charts.
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 provides explicit usage context: 'Use this when the model needs current, ready-to-use Szum chart configs or preferred semantic patterns.' It does not explicitly exclude alternatives or mention sibling tools, but the guidance is clear and actionable for selecting this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_preview_stateGet chart preview stateAUse this when the Szum chart App needs to restore a rendered preview as its current transient or saved view. It is read-only, owner-scoped when authenticated, and hidden from the model.
| Name | Required | Description | Default |
|---|---|---|---|
| previewId | Yes | Opaque 16-character chart-preview id |
| Name | Required | Description |
|---|---|---|
| chart | No | |
| status | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint. The description adds owner-scoped and hidden-from-model context, which is valuable beyond annotations. No contradiction.
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?
Two concise, front-loaded sentences. Every sentence adds unique value without unnecessary detail.
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 simple read-only tool with one parameter and comprehensive annotations, the description is complete and leaves no gaps.
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% with pattern description. The tool description does not describe the parameter beyond what's in the schema, which is acceptable given high coverage.
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 explicitly states the tool's purpose: 'restore a rendered preview as its current transient or saved view.' It is clear and specific, distinguishing it from siblings.
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 provides explicit 'when to use' guidance ('Use this when...'). However, it does not mention when not to use it or list alternatives among siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
list_chartsList chartsAUse this when the user wants to find charts in their saved library. Returns paginated metadata and URLs, not chart configs; requires authentication. Draft-only editor charts have publishedAt null, hasDraft true, and sizeBytes 0 because sizeBytes measures only the stored published config, not draft storage.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | Case-insensitive title substring search; trimmed and limited to 100 characters | |
| sort | No | Sort by creation time (default), update time, or title A-Z | |
| limit | No | Page size; defaults to 100 and has a maximum of 1000 | |
| cursor | No | Opaque nextCursor from the previous page | |
| source | No | Filter by one or more chart sources; omit to list all |
| Name | Required | Description |
|---|---|---|
| items | Yes | |
| total | No | Exact match count, present only for title searches |
| nextCursor | Yes | Opaque cursor for the next page, or null on the last page |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false. The description adds critical behavioral details: requires authentication, and explains the behavior for draft-only editor charts (publishedAt null, hasDraft true, sizeBytes 0). This adds significant value beyond 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 concise and front-loaded with the usage instruction. It consists of two sentences, each adding essential information with no filler. Every sentence 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 tool has 5 optional parameters, full schema coverage, and an output schema (not shown but indicated), the description covers purpose, authentication, and notable edge cases. It is complete enough for an AI agent to use correctly without additional context.
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 baseline is 3. The description does not add extra meaning beyond the schema; it mentions pagination implicitly but does not explain individual parameters. However, the schema is self-sufficient, so a 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 clearly states the tool's purpose: to list charts from the user's saved library. It specifies the return type (paginated metadata and URLs, not chart configs) and prerequisites (authentication). This clearly distinguishes it from sibling tools like get_chart or get_chart_config.
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 states when to use the tool ('when the user wants to find charts'), providing clear context. It does not explicitly list when not to use it or name alternatives, but the sibling tool list and the tool's purpose imply differentiation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
list_marksList mark typesAUse this when choosing or configuring chart mark types. Returns every available mark with its properties and defaults.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| marks | Yes | |
| shared | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description accurately reflects the read-only and non-destructive nature, consistent with the annotations (readOnlyHint=true, destructiveHint=false). It adds that the tool returns properties and defaults, providing full behavioral clarity.
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 long, front-loaded with the usage context, and contains no unnecessary 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 the simplicity of the tool (no parameters, output schema present), the description is complete. It explains when to use it and what it returns, which is sufficient for an agent to invoke it correctly.
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?
There are no parameters, so the description does not need to add parameter-level detail. The schema coverage is 100%, and the baseline for zero-parameter tools is 4.
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 that the tool returns every available mark with its properties and defaults, which clearly indicates the purpose. However, it does not explicitly differentiate from similar listing tools like list_charts or list_themes, but those are for different resources.
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 specifies when to use this tool: 'when choosing or configuring chart mark types.' This provides clear context, but it does not mention alternatives or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
list_themesList themesAUse this when choosing a visual theme for a chart. Returns every available theme and guidance on where each works best.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| themes | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so the agent knows it's safe. The description adds that the tool returns 'guidance on where each works best,' which provides behavioral context beyond annotations. No contradictions.
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 usage intent, and no wasted words. Every sentence contributes meaning.
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 no parameters and an output schema that presumably details the return structure, the description provides complete context: what the tool does and when to use it. No gaps.
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?
There are no parameters, so the description's mention of what is returned (themes and guidance) adds value. Schema coverage is 100%, so baseline is 3, but the description compensates by explaining the output nature.
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 clearly states the tool's function: listing visual themes for charts and providing guidance. It uses a specific verb ('Use this when choosing') and resource ('visual theme for a chart'), and distinguishes it from sibling tools like list_charts or list_marks.
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 'Use this when choosing a visual theme for a chart,' providing a clear context of use. It does not mention when not to use or alternatives, but given the simplicity of the tool (no parameters), this is sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
rename_chartRename chartAInspectUse this when the user wants to change a saved chart's library title without changing its config, publication state, or public URLs; requires authentication.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Opaque 32-character saved-chart id | |
| title | Yes | New saved-chart title; trimmed and limited to 200 characters |
| Name | Required | Description |
|---|---|---|
| id | Yes | Opaque 32-character saved-chart id |
| view | Yes | |
| title | Yes | Saved chart title |
| source | Yes | Chart origin; an open set of string values |
| editUrl | Yes | |
| embedUrl | Yes | Interactive-embed URL |
| imageUrl | Yes | Rendered-image URL |
| configUrl | Yes | Owner-only chart-config endpoint |
| createdAt | Yes | ISO-8601 creation timestamp |
| manageUrl | Yes | |
| sizeBytes | Yes | Compressed size of the stored published config, excluding drafts; 0 means no published config has been stored yet |
| updatedAt | Yes | ISO-8601 last-update timestamp |
| publishedAt | Yes | ISO-8601 publish timestamp, or null when public URLs are dark |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint=false (write operation) and destructiveHint=false. The description adds valuable detail: it only changes the library title, leaving config, publication state, and public URLs unchanged. It also explicitly states authentication requirement. No contradictions with 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 extremely concise with two sentences that front-load the usage trigger ('Use this when...'). Every word serves a purpose, no redundancy or fluff.
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 tool's simplicity, the description is adequately complete. It covers purpose, scope, and authentication requirement. Output schema exists, so no need to describe return values. Minor omission: does not mention whether the operation is synchronous or if it returns the updated chart, but output schema likely covers that.
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 baseline is 3. The tool description does not add new information about parameter formats beyond what the schema already provides (id pattern, title length limit). However, it does clarify the context of 'id' as the saved-chart id and that the title is for the library. This adds marginal value, so score remains at baseline.
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 clearly states the tool's purpose: renaming a saved chart's library title. It specifies the verb ('change a saved chart's library title') and the resource ('saved chart'), and differentiates from sibling tools by explicitly stating what it does NOT change (config, publication state, public URLs).
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 starts with 'Use this when...' providing explicit guidance for when to use the tool. It mentions requirement of authentication. While it does not list alternatives or when not to use, the context makes it clear this is for simple renames, distinguishing it from update_chart or other operations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
render_chartRender chartAInspectUse this when the user wants to preview or generate a chart. Validate each generated or changed config once before rendering, saving, or updating. Do not revalidate unchanged input; a successful render preflights it for later saves or updates. Errors block; warnings require explicit user approval for the exact config. Suggestions do not block. Replace the complete config with suggestedConfig and revalidate before repair. Stores a 1 hour preview and returns public image URLs. Authenticated previews use the account's render allowance, and each image produced from a returned URL is another render. Anonymous previews are complimentary; their images use the anonymous image allowance.
| Name | Required | Description | Default |
|---|---|---|---|
| config | Yes | Complete chart config JSON. Mark field references must match row keys. Chronological annual values use "YYYY" strings on an explicit UTC scale. Bar and area value axes stay linear and include zero. Explicit base-10 log scales require positive finite values and domains; use line or dot. Configure scales with top-level x/y; hide with display: false. Put shared data at chart level; use mark data for distinct rows. When rows share a bar position, map a series field to fill or stroke before setting group or aggregate. | |
| acknowledgeWarnings | No | Set true only after the user explicitly approves every warning returned for this exact config |
| Name | Required | Description |
|---|---|---|
| view | Yes | |
| title | Yes | |
| format | Yes | |
| imageUrl | Yes | |
| mimeType | Yes | |
| expiresAt | Yes | |
| validation | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses several behavioral traits beyond the annotations: rendering stores a 1-hour preview, returns public image URLs, consumes render allowances (with immediate charges for URL views), and distinguishes authenticated vs anonymous usage. It also clarifies error/warning/suggestion handling and the preflight effect, enriching what readOnlyHint=false and openWorldHint=true only imply.
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 dense but every sentence carries relevant information. It is roughly linear: usage, validation, error handling, replacement logic, then storage/allowances. Minor redundancy exists around validation (e.g., 'Do not revalidate unchanged input' and 'preflights it for later saves or updates' overlap slightly), but overall it is well-organized and not bloated.
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 tool's complexity (validation, allowances, preview lifecycle, public URLs), the description covers all key aspects without needing to explain return values since an output schema exists. It provides enough context for an agent to use the tool correctly, including error/warning handling and account/allowance implications. No obvious gaps remain.
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?
The schema already provides 100% coverage and detailed config and acknowledgeWarnings descriptions. The description adds extra meaning by explaining how warnings require explicit user approval for the exact config (mapping to acknowledgeWarnings) and how suggestedConfig should replace the complete config before revalidation. This goes beyond a bare schema but is not exhaustive.
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 opens with 'Use this when the user wants to preview or generate a chart,' clearly stating the specific action and resource. This distinguishes render_chart from siblings like validate_chart, save_chart, and update_chart by focusing on producing a visual preview or image.
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?
It tells exactly when to use the tool ('when the user wants to preview or generate a chart') and goes further to explain the validation workflow: validate once before rendering/saving/updating, don't revalidate unchanged input, and a successful render preflights for later saves/updates. This implicitly contrasts with validate_chart and shows how render fits into the overall lifecycle.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
save_chartSave chartAInspectUse this when the user wants to permanently save and publish a chart from a Szum config. Validate each generated or changed config once before rendering, saving, or updating. Do not revalidate unchanged input; a successful render preflights it for later saves or updates. Errors block; warnings require explicit user approval for the exact config. Suggestions do not block. Replace the complete config with suggestedConfig and revalidate before repair. Supply one idempotencyKey per intended chart and reuse it for retries. Returns permanent public Image and Embed URLs plus Edit and Studio links; requires authentication and saved-chart storage.
| Name | Required | Description | Default |
|---|---|---|---|
| config | Yes | Complete chart config JSON. Mark field references must match row keys. Chronological annual values use "YYYY" strings on an explicit UTC scale. Bar and area value axes stay linear and include zero. Explicit base-10 log scales require positive finite values and domains; use line or dot. Configure scales with top-level x/y; hide with display: false. Put shared data at chart level; use mark data for distinct rows. When rows share a bar position, map a series field to fill or stroke before setting group or aggregate. | |
| idempotencyKey | No | Stable retry key of at most 255 characters; reuse only for the exact same config | |
| acknowledgeWarnings | No | Set true only after the user explicitly approves every warning returned for this exact config |
| Name | Required | Description |
|---|---|---|
| id | Yes | |
| view | Yes | |
| title | Yes | |
| format | Yes | |
| editUrl | Yes | |
| embedUrl | Yes | |
| imageUrl | Yes | |
| mimeType | Yes | |
| manageUrl | Yes | |
| validation | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description goes far beyond annotations by detailing validation workflows (errors block, warnings require approval, suggestions don't block), idempotency key reuse, and the requirement for authentication. It also mentions return values and storage needs, providing rich behavioral context 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?
Though longer than typical, every sentence earns its place with actionable guidance. The description is front-loaded with purpose and proceeds through validation rules and return values in a logical order. No fluff or repetition.
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 complex save/publish tool with validation and idempotency, the description covers all essential aspects: when to use, validation rules, error/warning handling, idempotency, return values, and authentication. The output schema handles return structure, so the description is complete.
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 baseline is 3. The description adds operational semantics such as using idempotencyKey for retries, acknowledgeWarnings only after explicit approval, and replacing config with suggestedConfig for repair. This enriches understanding of how parameters are used.
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 opens with a specific verb and resource: 'permanently save and publish a chart from a Szum config.' This clearly distinguishes save_chart from siblings like render_chart or validate_chart. It also mentions returning permanent URLs, reinforcing the publish aspect.
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 states 'Use this when the user wants to permanently save and publish a chart,' which is clear usage context. However, it does not explicitly name alternatives like render_chart for preview-only use, though the distinction is easily inferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
update_chartUpdate chartAUse this when the user wants to replace and publish a saved chart's config while keeping its id and URLs. Validate each generated or changed config once before rendering, saving, or updating. Do not revalidate unchanged input; a successful render preflights it for later saves or updates. Errors block; warnings require explicit user approval for the exact config. Suggestions do not block. Replace the complete config with suggestedConfig and revalidate before repair. Refuses charts with unpublished editor changes; requires authentication and saved-chart storage.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Opaque 32-character saved-chart id | |
| config | Yes | Complete chart config JSON. Mark field references must match row keys. Chronological annual values use "YYYY" strings on an explicit UTC scale. Bar and area value axes stay linear and include zero. Explicit base-10 log scales require positive finite values and domains; use line or dot. Configure scales with top-level x/y; hide with display: false. Put shared data at chart level; use mark data for distinct rows. When rows share a bar position, map a series field to fill or stroke before setting group or aggregate. | |
| acknowledgeWarnings | No | Set true only after the user explicitly approves every warning returned for this exact config |
| Name | Required | Description |
|---|---|---|
| id | Yes | Opaque 32-character saved-chart id |
| view | Yes | |
| title | Yes | Saved chart title |
| source | Yes | Chart origin; an open set of string values |
| editUrl | Yes | |
| embedUrl | Yes | Interactive-embed URL |
| imageUrl | Yes | Rendered-image URL |
| configUrl | Yes | Owner-only chart-config endpoint |
| createdAt | Yes | ISO-8601 creation timestamp |
| manageUrl | Yes | |
| sizeBytes | Yes | Compressed size of the stored published config, excluding drafts; 0 means no published config has been stored yet |
| updatedAt | Yes | ISO-8601 last-update timestamp |
| validation | Yes | |
| publishedAt | Yes | ISO-8601 publish timestamp, or null when public URLs are dark |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description richly discloses behaviors beyond the annotations: it explains validation rules (validate once, no revalidation of unchanged input), error/warning/suggestion handling, the requirement for explicit user approval for warnings, and the preflight benefit of successful renders. It also discloses security/prerequisites (authentication, saved-chart storage) which the annotations do not cover. This is exemplary transparency.
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 dense but not bloated; each sentence covers a distinct behavioral aspect. It starts with a clear 'Use this when' statement and then structures into validation/error/requirement details. The length is justified by the tool's complexity, though a tiny bit of repetition (e.g., 'revalidate before repair') could be tightened.
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 tool's complexity (validation workflow, error handling, auth requirements), the description is remarkably complete. It covers when to use, the validation process, error/suggestion treatment, prerequisites, and blocking conditions. The output schema exists, so return values need not be described. No gaps are evident.
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?
The schema already provides detailed descriptions for all three parameters, giving 100% coverage. The description adds meaningful context beyond the schema, particularly around acknowledgeWarnings (tying it to the 'warnings require explicit user approval' rule) and the config replacement semantics ('Replace the complete config with suggestedConfig'). It slightly exceeds the baseline for full schema coverage.
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 clearly states the tool's specific purpose: 'replace and publish a saved chart's config while keeping its id and URLs.' This distinguishes it from siblings like save_chart (creating new charts), render_chart (previewing), and validate_chart (validation-only). The verb 'replace' and resource 'saved chart's config' are explicit.
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 opening phrase 'Use this when the user wants to replace and publish a saved chart's config' provides explicit usage context. It also gives guidance on validation behavior (when to validate vs. not) and conditions like 'refuses charts with unpublished editor changes.' However, it does not explicitly name alternative tools or state when not to use this tool, so it stops short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
validate_chartValidate chart configAUse this when a chart config will be rendered, saved, or updated. Validate each generated or changed config once before rendering, saving, or updating. Do not revalidate unchanged input; a successful render preflights it for later saves or updates. Errors block; warnings require explicit user approval for the exact config. Suggestions do not block. Replace the complete config with suggestedConfig and revalidate before repair. Read-only, free, and fast.
| Name | Required | Description | Default |
|---|---|---|---|
| config | Yes | Complete chart config JSON. Mark field references must match row keys. Chronological annual values use "YYYY" strings on an explicit UTC scale. Bar and area value axes stay linear and include zero. Explicit base-10 log scales require positive finite values and domains; use line or dot. Configure scales with top-level x/y; hide with display: false. Put shared data at chart level; use mark data for distinct rows. When rows share a bar position, map a series field to fill or stroke before setting group or aggregate. |
| Name | Required | Description |
|---|---|---|
| valid | Yes | |
| errors | Yes | |
| message | Yes | |
| diagnostics | Yes | |
| suggestedConfig | No | Schema version 2026-03-20. Send this JSON to POST https://szum.io/validate to validate it or POST https://szum.io/chart to render a chart image. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnlyHint annotation, the description discloses important behaviors: errors block, warnings require explicit user approval, suggestions do not block, and the need to replace config with suggestedConfig and revalidate before repair. It also notes the tool is read-only, free, and fast. This adds substantial context not covered by 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 efficient and front-loaded with the primary use case. Each sentence delivers actionable information—when to use, when not to, error/warning/suggestion handling, and repair workflow—without fluff.
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 presence of an output schema and the tool's single parameter, the description provides complete context. It covers the validation result semantics and repair process, which are essential for the agent to act correctly. No critical gaps.
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?
The schema description already covers 100% of the parameter, providing detailed rules about config structure. The tool description adds little about the input parameter itself aside from a minor hint about replacing with suggestedConfig, which is more about output handling. Therefore, baseline 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 clearly states the tool validates a chart config before rendering, saving, or updating. It specifies a distinct verb ('validate') and resource ('chart config'), and distinguishes it from sibling tools like render_chart or save_chart by focusing on the validation step.
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?
It explicitly states when to use the tool ('when a chart config will be rendered, saved, or updated') and when not to ('Do not revalidate unchanged input'). It also clarifies that a successful render preflights later saves/updates, giving clear context and exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
No comments yet. Be the first to start the discussion!
