Turn an English food description into an EFSA FoodEx2 code.
Scored across 2 tools
The two tools operate in completely different spheres: 'account_status' reports billing/quota without consuming credit, while 'encode' consumes credit to produce a FoodEx2 code. There is no plausible scenario where an agent would confuse which one to call.
Both names use snake_case and are immediately readable, which is good. However, one is a noun-based resource name (account_status) and the other a bare verb (encode) rather than a matching verb_noun pattern like get_account_status / encode_description, a minor deviation in an otherwise tiny surface.
The server's purpose is narrow — encode a food description and report quota — and each of the two tools serves that purpose directly with no filler. It sits at the thin end of the suggested range, but nothing obviously superfluous or missing at the tool-count level.
The primary encode workflow plus credit checking is covered, but the surface is one-directional: there is no reverse lookup (code to description), no batch encode for multi-item requests, and no way to browse or validate catalogue terms when a match fails. Agents hitting an unresolvable description have no fallback path.
Show remaining intro prepaid credit (USD and encodes left) or free-tier monthly encode quota for the signed-in email. Does not consume credit.
| Name | Required | Description | Default |
|---|---|---|---|
| confirm | No | Optional; set true if your client requires an argument. Ignored. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds real value by clarifying the two mutually exclusive result modes (prepaid credit vs. monthly free quota) and that calls are non-metered. It does not cover behavior on an unauthenticated/expired account or the response shape, but for a trivial read this is solid.
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, front-loaded with what is returned, ending with the key constraint ('Does not consume credit'). No filler or restated title.
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 zero-required-parameter read with no output schema, the description adequately covers both possible return modes and the account scope. Minor gap: it doesn't indicate what happens when no credit or no signed-in email exists, which matters since there's no output 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?
Only one optional parameter exists and the schema documents it fully ('Optional; set true if your client requires an argument. Ignored.'). The description says nothing about 'confirm', but with 100% coverage and a no-op parameter, the schema carries the burden completely.
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 concrete verb ('Show') and concrete resources (remaining intro prepaid credit in USD and encodes, or free-tier monthly encode quota), scoped to the signed-in email. It is clearly a read-only account lookup and implicitly distinct from the 'encode' sibling via 'Does not consume credit', though it never names that sibling.
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 line 'Does not consume credit' implies this is safe to call before encoding, and 'either/or' language implies it adapts to account type, but there is no explicit when-to-use vs. the 'encode' sibling or guidance on how often to poll it. Usage is inferable rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Turn one English food description (a food, drink, dish or meal) into a FoodEx2 code from the EFSA MTX catalogue: base term, facet descriptors for stated attributes the term does not imply, and labelled free text for what the code cannot express. Returns a short explanation of how the code was reached. Takes a few seconds for a direct name match, typically 15–25 seconds when the catalogue must be walked.
| Name | Required | Description | Default |
|---|---|---|---|
| description | Yes | The food description, e.g. 'fried rice with chicken' (at most 300 characters) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnly/openWorld annotations, it discloses latency characteristics ('a few seconds' vs 'typically 15–25 seconds') and that a short explanation is returned. This is genuine operational context an agent could not infer from annotations. It stops short of describing failure behavior for unmatchable descriptions.
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 compact sentences: output shape first, return value second, latency last. Each sentence carries distinct information and nothing is redundant with the schema.
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 value and does so ('base term, facet descriptors ... labelled free text', plus an explanation), and it covers timing for a slow tool. An agent knows what to send, what comes back, and what to expect on latency.
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 the baseline is 3, but the description adds real meaning: one description only, English, covering food/drink/dish/meal, and that stated attributes not implied by the base term become facets. That clarifies what content the single string should carry.
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 precise verb+resource transformation ('Turn one English food description ... into a FoodEx2 code from the EFSA MTX catalogue') and even names the output composition (base term, facets, free text). The only sibling, account_status, is unrelated, so there is no ambiguity to resolve.
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?
Makes clear the input is a single English food description (food, drink, dish or meal), which implicitly excludes non-food or multi-item inputs. It gives no explicit when-not-to-use or alternative path, but with only an unrelated sibling there is little to route against.
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.
account_statusencodeMaps a product description onto the category path of a marketplace taxonomy.
USDA FoodData Central nutrient lookup, FDA recall watch, EU FMCG labelling via remote MCP
AI-assisted English lexical records. Stored-only batch lookup; coverage and quality vary.
Classifies products into HS/HTS customs codes for import/export workflows. $0.10/call via x402.
Add one secure layer between your agents and this server.
