Read-only appliance parts lookup with current retail prices in USD, stock, purchase eligibility, product links, recorded model associations, fitment checks, and replacements. No API key required. Purchases are completed on globalpartsdistributor.com.
Scored across 4 tools
Each tool targets a distinct aspect: model-to-parts listing, part detail, substitution relationships, and fitment verification. lookup_model_parts and verify_fitment both touch fitment but differ in direction (enumerate vs. confirm), so boundaries are mostly clear.
Three tools follow a lookup_<noun> pattern, but verify_fitment deviates with a different verb. Still readable and predictable overall, with only a minor convention break.
Four tools is well within the reasonable range and each earns its place. It is slightly lean for the domain, with no free-text search or category browse, but not thin enough to be a problem.
The read-only lookup surface covers part identity, model fitment, pricing/stock, and substitutions—the core of a distributor lookup service. Minor gaps exist, such as keyword/description search or cross-brand comparison, but agents can work around them.
Return verified appliance parts recorded for an exact appliance model number.
| Name | Required | Description | Default |
|---|---|---|---|
| brand | No | ||
| limit | No | ||
| model | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds only a light provenance hint ('verified' parts 'recorded' for a model), and says nothing about result counts, truncation, or what an empty result means.
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?
One front-loaded sentence with no wasted words. It is efficient, though the brevity is part of why parameter and usage gaps remain.
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 3-param lookup with no output schema and 0% schema coverage, the description should say more: what 'brand' filters, what 'limit' bounds, and roughly what is returned. It covers the required 'model' param and the general return shape, but leaves the optional params and result semantics unaddressed.
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 for three undocumented params (model, brand, limit). It only conveys that 'model' must be exact; 'brand' and 'limit' are never explained in either place, leaving meaningful ambiguity for a filtering/pagination param.
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 ('Return verified appliance parts') and adds a meaningful constraint ('exact appliance model number'). However, it does not differentiate itself from siblings like lookup_part or lookup_substitution, so an agent must infer which of these to pick.
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 word 'exact' implies a usage condition (only pass a precise model number), which is useful implied guidance. But there is no explicit when-to-use/when-not-to-use statement and no sibling routing against lookup_part, lookup_substitution, or verify_fitment.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return exact appliance part identity, recorded models, and brand-qualified storefront retail price, stock, purchase eligibility, and product link.
| Name | Required | Description | Default |
|---|---|---|---|
| part | Yes | ||
| brand | No | ||
| limit | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered by structured data. The description usefully discloses that pricing is brand-qualified storefront retail and includes stock/eligibility/link, but says nothing about the limit/pagination behavior implied by the 'limit' parameter or about failure modes for unknown parts.
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?
A single dense sentence with the most important payload (exact part identity) front-loaded and no padding. It is efficient, though the long comma-list of return fields verges on a data dump.
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 no output schema, the description does the right thing by enumerating return values (identity, models, price, stock, eligibility, link). However, it omits result-set limits, matching behavior for ambiguous parts, and any distinction from the three sibling lookup tools, leaving the definition only minimally 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 0%: 'part', 'brand', and 'limit' have no documented meaning in the schema. The description only indirectly hints that 'brand' affects the price returned ('brand-qualified') and never explains 'part' matching rules or what 'limit' bounds (results? models?). With zero schema coverage the description should carry this burden and does not.
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 (Return) and a concrete resource set: appliance part identity, recorded models, brand-qualified retail price, stock, eligibility, and product link. This clearly separates it from verify_fitment or lookup_substitution in spirit, though it never names a sibling to make the boundary 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?
There is no statement of when to use this tool versus lookup_model_parts, lookup_substitution, or verify_fitment. The word 'exact' weakly implies it is not a substitution search, but the agent is left to infer the routing condition entirely.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return explicit recorded replacement or supersession relationships for an appliance part.
| Name | Required | Description | Default |
|---|---|---|---|
| part | Yes | ||
| brand | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and a closed-world scope, so the safety profile is covered. The description contributes the useful behavioral nuance that results are 'explicit recorded' relationships (not inferred or computed), but it says nothing about empty-result behavior, data freshness, or throttling.
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?
A single front-loaded sentence with no filler; the verb and result type lead. It is efficient, though the brevity is partly what leaves usage and parameter questions unanswered.
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 no output schema, the description carries the burden of describing the return shape, and it only gestures at it ('replacement or supersession relationships'). For a 2-parameter lookup with 0% schema description coverage, the definition is minimally sufficient but does not explain how relationships are represented or how brand affects the result.
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 0% and the description mentions only 'an appliance part', implicitly covering the required 'part' argument. The optional 'brand' parameter is never explained — whether it narrows the lookup, disambiguates part numbers, or is merely a filter — leaving a real gap the schema cannot fill.
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 (Return) and resource (recorded replacement/supersession relationships) scoped to appliance parts, so the agent knows this surfaces substitution data rather than a part's attributes. However, it never names or distinguishes itself from the immediate siblings lookup_part and lookup_model_parts, leaving the agent to infer the boundary.
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?
There is no when-to-use guidance: nothing tells the agent to reach for this tool when it needs to know whether a part is superseded versus using lookup_part for the part's own details. The phrase 'explicit recorded' hints that only stored relationships are returned and inference is excluded, but no alternative or exclusion is stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Verify whether an exact part number has a recorded fitment relationship with an exact appliance model. Never claim compatibility when verified_fit is false.
| Name | Required | Description | Default |
|---|---|---|---|
| part | Yes | ||
| model | Yes | ||
| part_brand | No | ||
| model_brand | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, idempotent, non-destructive and closed-world behavior, so the bar is lower. The description adds real value beyond them by naming the verified_fit result field and warning that compatibility must never be claimed when it is false — a meaningful interpretive constraint.
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 short sentences, front-loaded with the core action and followed by the critical output caveat. Every clause earns its place with no 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?
There is no output schema and no annotations gap in safety, and the description supplies the key return semantics (verified_fit) plus the interpretation rule. The remaining gap is the two brand parameters, which are left unexplained.
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?
With 0% schema description coverage, the description must carry the burden for four parameters. It conveys exact-match semantics for 'part' and 'model' but says nothing about part_brand or model_brand, leaving half the inputs undocumented in both structured and prose form.
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 (verify) and a precise resource/relationship (fitment between an exact part number and an exact appliance model), which is clearly distinct from lookup-oriented siblings. It does not explicitly name which sibling to prefer, so it stops 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?
The use case is implied by 'verify whether ... has a recorded fitment relationship' and the emphasis on 'exact' suggests it is not for fuzzy or substitution lookups, but no explicit when-to-use/when-not or routing to lookup_substitution / lookup_model_parts is given. Usage must be inferred.
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.
lookup_model_partslookup_partlookup_substitutionverify_fitment
Add one secure layer between your agents and this server.