Bounded footwear fit checks for a specific shoe, person, and intended use.
Scored across 1 tool
With only one tool, there is no inter-tool ambiguity; its purpose is clearly bounded to finished footwear fit checks. The description's many exclusions narrow the scope further, making misselection essentially impossible.
The single tool name check_footwear_fit follows a clear snake_case verb_noun convention. With only one tool, there is no possibility of inconsistent naming across the set.
A single tool is borderline thin for a shoe-fit domain, even though this tool is nontrivial and focused. Related operations such as product lookup, fit comparison, or history are absent, making the surface feel under-scoped.
The tool only covers three limited prototype pathways and explicitly cannot judge heel retention, blisters, or traction. For a general shoe fit checker, this leaves significant gaps that could cause agent failures on common fit questions.
Use for a specific finished footwear product and the person's reported interaction. English is the primary consumer-language coverage; full Chinese interpretation is deferred. Without a complete approved canonical request, the three limited prototype paths are activity-related compression or numbness, instep pressure with a width comparison, and downhill toe-front contact. Heel retention, blister and ground-traction concerns can be acknowledged but cannot receive a new formal judgment or corrective prescription here. Prototype results are not formal Core conclusions. Do not use for cross-brand recommendations, product ranking, generic shoe education, style advice, simple size conversion, or medical diagnosis/treatment. When presenting a returned fit judgment, preserve the tool's decision, unknowns, next steps, alternatives, professional boundary, evidence state, and execution provenance. When coreJudgment is present, preserve its primaryState, reasonCodes, criticalUnknownIds, Case/Rule Set identity, and do not replace them with stronger host conclusions. Do not add or strengthen unverified product facts, gait or biomechanical labels, medical causal explanations or diagnoses, or extra size/width/lacing/product prescriptions unless they were independently established as verified evidence in the request. Keep any separately sourced external information clearly separate from the bounded fit judgment.
| Name | Required | Description | Default |
|---|---|---|---|
| product | Yes | ||
| evidence | No | ||
| question | Yes | ||
| useContext | No | ||
| bodySignals | No | ||
| canonicalRequest | No | Optional complete governed Match & Fit Core JudgmentRequest. It is passed through without semantic field invention and is canonical only if the configured Core executor validates and executes it. | |
| interactionSignals | No |
| Name | Required | Description |
|---|---|---|
| why | Yes | |
| boundary | No | |
| decision | Yes | |
| unknowns | Yes | |
| nextSteps | Yes | |
| provenance | No | |
| alternatives | No | |
| coreJudgment | No | |
| currentAssessment | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Far exceeds the readOnly/idempotent annotations by disclosing that this is a limited prototype with only three functioning paths, that results are 'not formal Core conclusions,' that some concerns (heel retention, blister, traction) cannot receive a formal judgment, and that a full canonical request is required for complete operation. It also specifies preservation rules for coreJudgment (primaryState, reasonCodes, Case/Rule Set identity) and forbids host strengthening of unverified facts.
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 long, dense, and jargon-laden ('primaryState, reasonCodes, criticalUnknownIds, Case/Rule Set identity', 'execution provenance'), with layered preservation rules that are hard to parse. Front-loading is weak: it opens with 'Use for...' and buries the actual scope constraint mid-paragraph, and several sentences restate the same non-conclusion boundary.
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 the description does cover the operational envelope and output-preservation duties richly. However, for a tool with 7 largely undocumented parameters, it is too vague about the input contract (especially how a 'canonical request' is formed and what evidence/body/interaction signals mean), so it is only adequately 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 description coverage is only 14% across 7 parameters, so the description must carry the load, and it largely does not. It alludes to canonicalRequest ('Without a complete approved canonical request') and to interaction/body signals indirectly ('the person's reported interaction'), but never explains product, evidence, question, useContext, bodySignals, or interactionSignals, leaving most fields ambiguous.
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 never plainly states what the tool produces (a bounded fit judgment for a specific shoe/person); the closest is 'Use for a specific finished footwear product and the person's reported interaction,' which is usage framing rather than a purpose statement. The three limited prototype paths and the note about 'a returned fit judgment' let an agent infer the function, but the core verb+resource is buried under governance language.
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 explicit when-not-to-use conditions ('Do not use for cross-brand recommendations, product ranking, generic shoe education, style advice, simple size conversion, or medical diagnosis/treatment') and names the three in-scope prototype paths (activity compression/numbness, instep pressure with width comparison, downhill toe-front contact). No siblings exist to route to, so this is near-complete, though the when-to-use side is expressed as 'limited prototype paths' rather than a crisp trigger.
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.
check_footwear_fit7 fields changedInput schema / properties / canonicalRequestAdded value: +{
+ "anyOf": [
+ {
+ "additionalProperties": true,
+ "type": "object"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Optional complete governed Match & Fit Core JudgmentRequest. It is passed through without semantic field invention and is canonical only if the configured Core executor validates and executes it.",
+ "title": "Canonicalrequest"
+}Output schema / $defs / CoreJudgmentAdded value: +{
+ "additionalProperties": false,
+ "properties": {
+ "caseId": {
+ "title": "Caseid",
+ "type": "string"
+ },
+ "caseVersion": {
+ "title": "Caseversion",
+ "type": "string"
+ },
+ "criticalUnknownIds": {
+ "items": {
+ "type": "string"
+ },
+ "title": "Criticalunknownids",
+ "type": "array"
+ },
+ "executionId": {
+ "title": "Executionid",
+ "type": "string"
+ },
+ "packageId": {
+ "title": "Packageid",
+ "type": "string"
+ },
+ "primaryState": {
+ "title": "Primarystate",
+ "type": "string"
+ },
+ "reasonCodes": {
+ "items": {
+ "type": "string"
+ },
+ "title": "Reasoncodes",
+ "type": "array"
+ },
+ "ruleSetId": {
+ "title": "Rulesetid",
+ "type": "string"
+ },
+ "ruleSetVersion": {
+ "title": "Rulesetversion",
+ "type": "string"
+ }
+ },
+ "required": [
+ "primaryState",
+ "reasonCodes",
+ "criticalUnknownIds",
+ "packageId",
+ "executionId",
+ "caseId",
+ "caseVersion",
+ "ruleSetId",
+ "ruleSetVersion"
+ ],
+ "title": "CoreJudgment",
+ "type": "object"
+}Output schema / $defs / Provenance / properties / adapterMode / constRemoved value: -"PROTOTYPE_RULES"Output schema / $defs / Provenance / properties / adapterMode / enumAdded value: +[
+ "PROTOTYPE_RULES",
+ "CANONICAL_CORE"
+]Output schema / $defs / Provenance / properties / canonicalCoreExecuted / constRemoved value: -falseOutput schema / $defs / Provenance / properties / coreBaseline / constRemoved value: -"phase-1-approved-baseline@7da520058257362a35c88173c3cd03d37c8965c8"Output schema / properties / coreJudgmentAdded value: +{
+ "anyOf": [
+ {
+ "$ref": "#/$defs/CoreJudgment"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null
+}check_footwear_fitSize-aware ADV/dual-sport motorcycle gear: sizing, fit guides, verified deals (read-only).
Free, read-only truck and Jeep parts fitment: what fits your vehicle, fit checks, tire sizes.
Find offers that fit what you want, ranked by fit only, with links to buy.
Public fitness and nutrition calculators, exercise information, and evidence-based guides.
Add one secure layer between your agents and this server.
