UK Food Recall Alerts MCP

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must carry behavior, and it does disclose the return payload fields and the ~200-alert scope bound. It omits that access_token is required for subscriber access, whether results are paginated, and what happens when nothing matches—gaps that matter for an unannotated tool.

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 tightly packed sentence that front-loads the return payload, which is what distinguishes this tool. The 'PRO.' prefix is noise that doesn't earn its place.

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?

No output schema exists, and the description does a reasonable job of enumerating returned fields. However, for a 3-parameter search with no annotations and zero required parameters, the definition should clarify auth/tier requirements and the behavior with no matches or an empty result set.

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 67%; the description loosely maps its 'keyword/allergen/type' phrasing onto keyword, kind, and the allergen concept. It adds no matching semantics, wildcard behavior, or explanation of how allergen filtering differs from keyword search, so it does little beyond 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?

The description names a specific resource (alerts) and states exactly what is returned (products, batch codes, best-before, risk statement) plus the scope (~last 200 alerts). It is distinguishable from latest_alerts/new_since by being a filtered search rather than a recency feed, though it never names those siblings directly and the leading 'PRO' tier marker is unexplained.

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?

Usage is implied by 'matching keyword/allergen/type', giving an agent a rough sense of when this applies, and the ~200-alert window hints at its limits. But there is no explicit when-to-use versus latest_alerts/new_since/watchlist, and no stated fallback when the alert is outside the search window.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description does disclose useful traits: a hard cap of 5 results, the FSA as source, and that access is free (no billing/auth barrier). It does not cover pagination limits, whether filtering is server-side, or what happens on zero matches, so significant behavioral burden remains undisclosed.

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 compact sentence with the core scope and filter semantics front-loaded. The leading 'FREE.' is arguably noise unless it is meant to signal no cost/auth, but nothing else is wasted.

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 one-optional-param tool with no output schema, the description covers scope, count, and filter semantics but says nothing about the shape of returned records (dates, product names, alert type, URLs). An agent knows what it will get conceptually, not structurally.

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%, so the description must carry the parameter — and it does, explaining that 'keyword' matches product, brand, or allergen and that it is optional. It lacks match semantics (substring vs exact, case sensitivity), which keeps it below 5.

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 resource (latest 5 UK food recalls and allergy alerts from the FSA) and the optional filter dimension (product, brand, allergen). An agent can distinguish it from alert_search and new_since by the 'latest 5' snapshot framing, though it never names those siblings explicitly.

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 phrase 'Latest 5' implies this is a quick recency snapshot and the optional keyword implies filtering, but there is no explicit when-to-use vs. alert_search or watchlist guidance. 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.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden. It does disclose the PRO/tier gating and the 'default yesterday' behavior, but says nothing about auth needs (access_token is only in the schema), output shape, ordering, or result limits — significant gaps for a no-annotation tool.

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 compact sentence with the scope stated up front and zero filler. The 'PRO.' prefix is terse but does front-load the tier requirement; only the em-dash aside 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?

For a simple two-parameter read tool with no output schema, the description covers purpose and default but leaves return values, ordering, and the auth requirement to the schema. Adequate but with clear gaps an agent must infer.

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%, so both parameters are already documented, and the baseline is 3. The description adds the useful detail that 'since' defaults to yesterday, but gives no date-format or token-handling guidance beyond 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 the resource (alerts) and the temporal scope (published since a date, default yesterday), which is specific enough to distinguish it from latest_alerts at a glance. It does not explicitly name or contrast the siblings, so a 4 rather than 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?

'daily check for your agent' implies a polling/recency workflow, giving implied usage. It never says when to prefer alert_search or latest_alerts instead, and there are no exclusions, so guidance is only implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With zero annotations the description carries the full burden, and it does disclose two real behavioral facts: the 100-item cap and that this is a paid 'PRO' feature. It does not say what is returned (matched alerts? counts?), how tokens are validated, or how partial/zero matches are handled.

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 tight sentence, front-loaded with the PRO gating followed by the core action and the audience. Nothing is wasted, though the dangling 'PRO.' opener is terse to the point of being cryptic.

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 tool with no annotations and no output schema, the definition tells an agent what to send but not what it will get back or how results are shaped, which is a meaningful gap for a lookup whose entire value is the match results.

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 50% and the required 'items' array has no schema description; the description compensates by defining its contents (brands/suppliers/products) and the 100-element limit. It still says nothing about matching semantics (exact vs fuzzy names), and access_token is left entirely 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 specific verb and resource: check a list of brands/suppliers/products against recent alerts, with a batch size cap of 100. The batch-of-your-own-entities framing distinguishes it from siblings like alert_search and latest_alerts, though it names none of them explicitly.

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 audience line (retailers, caterers, wholesalers) implies the use case of batch-verifying a stock list, but there is no explicit when-to-use or when-not guidance and no reference to the very similar alternatives alert_search and new_since.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.