Choose a palette, compare digital colors and create portable outfit, event or packing boards.
Scored across 6 tools
Most tools have clearly distinct purposes: compare_colors compares colors, the board create/get pair handles artifacts, and the quiz tools handle self-assessment. However, select_palette and score_color_quiz both output a 12-color palette and could occasionally be confused, though their distinct input paths (season choice vs eight answers) help differentiate them.
All six tools follow a clean verb_noun snake_case pattern (compare_colors, create_palette_board, get_palette_board, get_quiz_questions, score_color_quiz, select_palette). No style mixing or vague verbs; the pattern is fully predictable.
Six tools is well-scoped for a palette/color analysis server, with each tool mapping to a distinct capability (comparison, board generation/retrieval, quiz questions, scoring, selection). Nothing feels redundant or missing from a count perspective.
The surface covers a solid lifecycle: quiz questions, quiz scoring, palette selection with revision support, color comparison, and board creation/retrieval. There is no explicit delete or update operation for palettes, but revisions are handled via select_palette with a prior reference, leaving only minor gaps.
Compare up to 12 supplied six-digit hex colors or standard color names with a portable selected palette. Unknown or ambiguous names request hex values. Return the nearest digital swatch with a fixed RGB rule and concise rationale. This does not assess skin, photos, fabrics or garments you own.
| Name | Required | Description | Default |
|---|---|---|---|
| colors | Yes | ||
| palette_ref | Yes |
| Name | Required | Description |
|---|---|---|
| kind | Yes | |
| result | Yes | |
| schema_version | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, idempotent, non-destructive and closed-world. The description adds real value on top: a 12-color cap, the fallback behavior for unknown or ambiguous names, and the nature of the output (nearest swatch via a fixed RGB rule plus rationale). It stops short of describing determinism or error handling in detail.
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 dense sentences, front-loaded with the verb and resource, with no filler. The disambiguation sentence and the scope exclusion each earn their place, though the wording is slightly compressed.
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?
An output schema exists, so return values need not be described, and annotations cover the safety profile. The one meaningful gap is the provenance and expected structure of `palette_ref`, which an agent calling this tool cold would not know how to supply.
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 0%, so the description carries the full burden. It compensates well for `colors` (accepts six-digit hex or standard names, up to 12) but says nothing about `palette_ref` beyond the vague word 'portable' — its origin, format or expected content are 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?
States a specific verb and resource: 'Compare up to 12 supplied six-digit hex colors or standard color names with a portable selected palette.' An agent can tell what it does and the input ceiling, but the description never names or contrasts a sibling tool (e.g. select_palette), so differentiation from the rest of the palette suite is left to inference.
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 supplies one exclusion ('does not assess skin, photos, fabrics or garments you own') and a fallback for bad input, but gives no explicit when-to-use rule or named alternative. The phrase 'a portable selected palette' hints that palette_ref must already exist, yet it doesn't say where to obtain it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate a labeled downloadable SVG board and matching 12-color PNG from a user-confirmed palette, a chosen outfit/event/packing purpose and optional supplied garment colors. Requires the user’s chosen palette; unknown colors request clarification. Computation only; no upload, charge, account record or closet inference.
| Name | Required | Description | Default |
|---|---|---|---|
| colors | No | ||
| purpose | Yes | ||
| occasion | No | ||
| palette_ref | Yes |
| Name | Required | Description |
|---|---|---|
| kind | Yes | |
| result | Yes | |
| schema_version | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/idempotent/non-destructive/closed-world, and the description adds genuinely new context: it is computation-only with no upload, charge, account record, or closet inference, and it clarifies unknown colors trigger a clarification request. That supplements the safety profile rather than restating it.
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 dense sentences, front-loaded with the generated artifacts before the prerequisites and side-effect disclaimers. No filler, though the clause-heavy final sentence is densely packed.
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?
An output schema exists so return values need no explanation, and the description covers purpose, precondition, and side-effect boundaries well. The main gap is the undocumented "occasion" input, which an agent would have to discover from the schema.
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 0%, so the description must carry the load: it covers palette_ref, purpose (outfit/event/packing), and optional garment colors, but omits the "occasion" parameter entirely and does not explain that colors may be given as hex or name. Partial compensation for a 4-parameter tool.
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 (Generate) and concrete resources (labeled downloadable SVG board and matching 12-color PNG), plus the inputs that drive them. It is distinguishable from the retrieval-style sibling get_palette_board and from select_palette/compare_colors, though it never names a sibling outright.
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?
"Requires the user's chosen palette; unknown colors request clarification" gives a precondition and a fallback behavior, which is real usage guidance. However, it never says when to pick this tool over select_palette or get_palette_board, so the routing is only implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Reconstruct the same SVG, PNG, selected palette and supplied-color comparisons from a complete board reference. Anyone with a reference can read its public palette data. It is not an account credential and cannot retrieve purchased reports. No Tonebook server record is required.
| Name | Required | Description | Default |
|---|---|---|---|
| board_ref | Yes |
| Name | Required | Description |
|---|---|---|
| kind | Yes | |
| result | Yes | |
| schema_version | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false. The description adds meaningful behavioral context beyond them: access requires only a public board reference, no account credential, no Tonebook server record, and cannot retrieve purchased reports.
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 purpose is front-loaded in the first sentence, followed by short access and limitation sentences. The final two sentences are closely related and could be tightened, but overall the text is compact and every sentence carries relevant information.
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?
An output schema exists, so the description need not explain return values, and annotations cover safety. The description supplies retrieval scope and access caveats; only minor edge-case details around bad or incomplete references are left implicit.
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 0%, so the description must compensate. It adds that board_ref is a 'complete board reference' and is public/portable, but it does not explain the reference format, where to obtain it, or what constitutes 'complete'.
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: 'Reconstruct the same SVG, PNG, selected palette and supplied-color comparisons from a complete board reference.' It clearly describes retrieval of a palette board, but it does not explicitly contrast with siblings like create_palette_board or select_palette, so it falls short of a 5.
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 gives useful access context ('Anyone with a reference can read its public palette data') and a negative constraint ('cannot retrieve purchased reports'), which implies when the tool is applicable. However, it never names or compares against sibling tools, so the agent must infer when to choose this over alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return Tonebook’s eight categorical self-assessment questions. Ask for the user’s own choices; do not infer choices from a photo or conversation history. No account, photo or payment is needed.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| kind | Yes | |
| result | Yes | |
| schema_version | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish read-only, idempotent, non-destructive and closed-world behavior, so the bar is low. The description still adds value by asserting no auth/payment is required and by constraining how the data should be obtained, which is behavioral context not present in 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?
Three short sentences, front-loaded with what is returned, then the usage constraint, then the prerequisite. No filler or redundant restatement of the name.
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?
An output schema exists, so return values need no explanation, and the description covers purpose, the key usage constraint, and prerequisites for a no-parameter read tool. Nothing needed to call it correctly is missing.
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 tool takes zero parameters, so per the baseline this scores 4. There is nothing for the description to clarify beyond the empty schema, which it correctly does not pad.
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+resource: returns Tonebook's eight categorical self-assessment questions, with the count and nature of the payload. It does not explicitly distinguish itself from the sibling score_color_quiz, but the 'questions' vs. 'score' framing makes the split inferable.
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 when/how guidance: ask the user for their own choices and do not infer them from a photo or conversation history, plus prerequisites (no account, photo or payment). It stops short of naming sibling alternatives or a sequencing rule, so it is strong context rather than full routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Use eight explicit user-selected answers to suggest a 12-color starting palette and adjacent option. Uncertain or conflicting preferences prompt clarification. The versioned result is unconfirmed guidance, not a diagnosis. It never overwrites a confirmed palette.
| Name | Required | Description | Default |
|---|---|---|---|
| contrast | Yes | What is your overall feature contrast? | |
| eye_color | Yes | What is your eye color? | |
| undertone | Yes | Which colors do you prefer near your face? | |
| skin_depth | Yes | How would you describe your skin depth? | |
| natural_hair | Yes | What is your natural hair color? | |
| metal_preference | Yes | Which metal look do you prefer near your face? | |
| white_preference | Yes | Which white do you prefer wearing? | |
| complimented_colors | Yes | Which colors have drawn compliments on you? |
| Name | Required | Description |
|---|---|---|
| kind | Yes | |
| result | Yes | |
| schema_version | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare a safe read-only, idempotent, non-destructive operation, and the description adds behavioral context beyond that: results are versioned, unconfirmed guidance and never overwrite a confirmed palette. That overwrite-protection detail is useful state information not found in the structured fields.
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 short sentences, front-loaded with the action and output, then constraints and behavioral caveats. No repetition or filler.
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 read-only scoring tool with full schema coverage and an output schema, the description covers inputs, output, uncertainty handling, versioning, and the no-overwrite guarantee. Nothing needed to invoke it correctly is missing.
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 all eight parameters documented and enum-constrained, so the schema already carries parameter semantics. The description adds that exactly eight explicit answers are expected, but gives no per-parameter or combination guidance beyond that.
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: use eight answered preferences to suggest a 12-color starting palette plus an adjacent option. This distinguishes it from siblings like get_quiz_questions, select_palette, or compare_colors by describing its unique derivation role.
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 clearly indicates the context of use: after the eight explicit answers are collected, and that uncertainty/conflict prompt clarification rather than a forced result. It does not name when to choose compare_colors or create_palette_board instead, so it stops short of full alternative routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return a portable user-confirmed palette from an explicit season choice. For correction, pass the prior palette reference so source and revision are retained. Confirm only the user’s stated choice. Keep the new reference for later calls; this does not write account or native report data.
| Name | Required | Description | Default |
|---|---|---|---|
| confirmed | Yes | ||
| season_id | Yes | ||
| previous_palette_ref | No |
| Name | Required | Description |
|---|---|---|
| kind | Yes | |
| result | Yes | |
| schema_version | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the safety profile is largely covered. The description adds genuine value beyond them: it clarifies this 'does not write account or native report data' (reconciling the write-sounding name) and instructs the agent to retain the returned reference for later calls.
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 tightly-scoped sentences, front-loaded with the core purpose. The correction path, confirmation constraint, and non-write disclaimer each add a distinct fact with little filler.
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, return values need no explanation, and annotations cover safety. The description adds the correction workflow and the negative 'does not write' clarification, making it complete enough for an agent to call this 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?
Schema description coverage is 0%, so the description must carry the load. It meaningfully maps 'explicit season choice' to season_id and 'prior palette reference' to previous_palette_ref for correction. The const confirmed parameter is only indirectly addressed ('Confirm only the user's stated choice'), leaving syntax/format details to the schema.
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 clear verb+resource: 'Return a portable user-confirmed palette from an explicit season choice.' This distinguishes it from create_palette_board and get_palette_board by signaling a confirmation/normalization step rather than a retrieval or creation. It stops short of explicitly naming the siblings it differs from.
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?
'For correction, pass the prior palette reference...' and 'Confirm only the user's stated choice' give clear conditional guidance for the two modes (confirm vs correct). No explicit exclusions or named alternative tools, but the use context is unambiguous.
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.
compare_colorscreate_palette_boardget_palette_boardget_quiz_questionsscore_color_quizselect_paletteA complete color workflow over MCP: mix, convert, harmonize, measure, place, and remember palettes.
Convert colours between hex, RGB, HSL, OKLCH and CMYK, and compute harmonies.
Solve, audit and simulate colorblind-safe chart palettes. WCAG contrast, OKLab ΔE. Read-only.
Every UK paint colour, matched across brands by ΔE and priced; palettes, planner projects, trends.
Add one secure layer between your agents and this server.