Identify a catalog product from a name, CompatAir or merchant URL, EAN/GTIN, MPN, evidenced distributor SKU, reference, or stable CompatAir ID. No network fetch is performed.
| Name | Required | Description | Default |
|---|---|---|---|
| ean | No | ||
| url | No | ||
| limit | No | ||
| query | No | ||
| reference | No |
| Name | Required | Description | Default |
|---|---|---|---|
| matches | No | ||
| verdict | Yes | ||
| limitations | Yes | ||
| next_actions | Yes | ||
| canonical_url | Yes | ||
| verdict_scope | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Output schema / additionalPropertiesPrevious value: -falseNew value: +trueOutput schema / properties / canonical_follow_urlRemoved value: -{
- "format": "uri",
- "type": "string"
-}Output schema / properties / catalogVersionRemoved value: -{
- "type": "string"
-}Output schema / properties / catalog_versionRemoved value: -{
- "type": "string"
-}Output schema / properties / engineVersionRemoved value: -{
- "type": "string"
-}Output schema / properties / errorRemoved value: -{
- "additionalProperties": false,
- "properties": {
- "code": {
- "enum": [
- "invalid_arguments",
- "insufficient_data"
- ],
- "type": "string"
- },
- "message": {
- "type": "string"
- },
- "retryable": {
- "type": "boolean"
- },
- "scope": {
- "const": "request"
- }
- },
- "required": [
- "code",
- "message",
- "scope",
- "retryable"
- ],
- "type": "object"
-}Output schema / properties / matches / items / additionalPropertiesPrevious value: -falseNew value: +trueOutput schema / properties / matches / items / properties / brandRemoved value: -{
- "type": "string"
-}Output schema / properties / matches / items / properties / compat_air_idRemoved value: -{
- "type": "string"
-}Output schema / properties / matches / items / properties / eanRemoved value: -{
- "type": "string"
-}Output schema / properties / matches / items / properties / labelRemoved value: -{
- "type": "string"
-}Output schema / properties / matches / items / properties / modelRemoved value: -{
- "type": "string"
-}Output schema / properties / matches / items / properties / mpnRemoved value: -{
- "type": "string"
-}Output schema / properties / matches / items / properties / slugRemoved value: -{
- "type": "string"
-}Output schema / properties / matches / items / requiredPrevious value: -[
- "compat_air_id",
- "type",
- "id",
- "slug",
- "brand",
- "model",
- "canonical_url"
-]New value: +[
+ "id",
+ "type",
+ "match_confidence",
+ "canonical_url"
+]Output schema / properties / method_versionRemoved value: -{
- "type": "string"
-}Output schema / properties / observed_atRemoved value: -{
- "format": "date",
- "type": "string"
-}Output schema / properties / product_urlsRemoved value: -{
- "items": {
- "format": "uri",
- "type": "string"
- },
- "type": "array",
- "uniqueItems": true
-}Output schema / properties / source_urlsRemoved value: -{
- "items": {
- "format": "uri",
- "type": "string"
- },
- "type": "array",
- "uniqueItems": true
-}Output schema / properties / verdict_schema_versionRemoved value: -{
- "const": "2.0.0"
-}Output schema / requiredPrevious value: -[
- "verdict",
- "verdict_scope",
- "verdict_schema_version",
- "canonical_url",
- "product_urls",
- "source_urls",
- "method_version",
- "catalog_version",
- "observed_at",
- "limitations",
- "next_actions",
- "catalogVersion",
- "engineVersion"
-]New value: +[
+ "verdict",
+ "verdict_scope",
+ "canonical_url",
+ "limitations",
+ "next_actions"
+]Output schema / properties / canonical_follow_urlAdded value: +{
+ "format": "uri",
+ "type": "string"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, which cover safety and idempotency. The description adds value by noting 'No network fetch is performed,' which is a behavioral detail not captured in 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?
Two concise sentences with no superfluous content. The first sentence lists all identifier types, front-loading the key information. Every word contributes to understanding the tool's function.
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 description covers the main purpose and identifier types but lacks details on return values, handling of multiple matches (given the 'limit' parameter), or behavior when conflicting identifiers are provided. Given the output schema exists, it partially compensates, but ambiguity remains.
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 schema description coverage at 0%, the description must compensate. It lists identifier types (name, URL, EAN, etc.) but does not explicitly map them to parameter names (e.g., which parameter accepts 'MPN' or 'merchant URL'). The 'limit' parameter is not mentioned at all. This leaves ambiguity in parameter selection.
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 identifies a catalog product from a specific list of identifiers (name, URL, EAN, etc.). It distinguishes itself from sibling tools like find_compatible_alternatives and evaluate_air_compatibility by focusing on identification rather than compatibility or alternatives.
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 implies usage for looking up products by various identifiers but does not explicitly specify when to use this tool over others like search_knowledge. The statement 'No network fetch is performed' gives some context but no direct comparison to alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct purpose: building systems, evaluating compatibility, finding alternatives, retrieving offers, identifying products, routing questions, and searching knowledge. No two tools overlap in functionality.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., build_complete_air_system, identify_product). The verbs are imperative and clearly indicate the action.
Seven tools is an appropriate number for the domain of pneumatic air systems. Each tool covers a specific aspect without being too few or too many, providing a well-scoped interface.
The tool set covers the main workflows: identification, compatibility evaluation, system building, alternatives, offers, and knowledge search. Minor gaps like detailed product specifications could exist, but the core functionality is complete.