FlowFresh SA fruit reference data

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world, so safety behavior is covered. The description adds a genuinely useful scope caveat (information only; FlowFresh does not broker fruit), which helps an agent avoid misusing it as a commercial contact. It does not disclose what the tool actually returns or how the contact route is presented, so the added value is moderate.

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 parenthetical caveat earns its place by constraining the tool's purpose.

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 parameters and no output schema, the description carries the burden of explaining what the agent gets back, and it stops short of saying so—there is no indication of whether it returns an address, email, phone number, or form. For a simple static lookup this is adequate but leaves a real gap in what to expect from the call.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline of 4 applies. No parameter omissions or misrepresentations are present.

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 states a clear purpose: it is a contact route for enquiries about the reference data, i.e. how to reach FlowFresh. The verb is slightly indirect ('How to reach...') rather than a crisp 'Returns contact details', but the resource and intent are unambiguous. It does not explicitly distinguish itself from siblings like get_specs or list_products, though the contact/information framing implicitly separates it.

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 only implied: an agent gathers that this tool is for reaching FlowFresh rather than retrieving product or season data. The disclaimer 'FlowFresh does not buy, sell or broker fruit' usefully scopes the kind of enquiry that is appropriate. There is no explicit when-to-use vs alternatives statement or prerequisite guidance.

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?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower; the description still adds genuine behavioral context the annotations lack: each line is labelled Fact/Inference/pending with dated sources, and the covered jurisdictions are enumerated. The reliability/provenance disclosure and the 'not regulatory advice' disclaimer are exactly the kind of extra context that earns credit above the annotation baseline.

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 purpose and content scope, then the Fact/Inference provenance and the legal disclaimer. Dense but every clause carries information; the long jurisdiction list is the only mildly bulky element.

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 takes on the burden of describing returns, and it does so reasonably: labelled lines, dated sources, enumerated jurisdictions. For a two-param read-only lookup that is nearly complete; only the absence of explicit usage/routing guidance and any hint of data recency limits leaves a small gap.

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 both parameters are already documented ('Product id from list_products', destination examples). The description restates the same destination list but adds no syntax, format, casing, or fallback guidance for unknown values, so it neither compensates for a gap nor adds meaning beyond the schema. Baseline 3.

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 verb+resource ('Plant-health market-access notes for a South African fruit to a destination') and enumerates the content an agent will get: entry eligibility, certificate/permit steps, protocol requirements, cold treatment. It is clearly distinct in domain from siblings like get_specs or get_season, though it never names or contrasts those siblings explicitly, which holds it at a 4.

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 the product/destination framing, but there is no explicit when-to-use statement, no prerequisite (e.g. 'resolve product via list_products first'), and no routing away from alternatives such as get_specs or contact_route. The 'Information only; not regulatory advice' line is a caveat, not guidance on when to invoke.

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?

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds real value beyond that: the output is line-oriented, each line carries a Fact/Inference provenance label with its source, and the value is expressed in ISO weeks/months — none of which the annotations or schema convey.

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 compact sentences, front-loaded with the resource and scope, with the optional-parameter rule placed last where it belongs. No filler or restatement of the 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?

There is no output schema, so the description correctly carries the return-shape burden by describing line labels and provenance. Combined with the annotation coverage and a simple one-parameter read, an agent has enough to call it correctly; only multi-product return details are left unstated.

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% and the single parameter's origin (list_products) is already documented in the schema, so baseline is 3. The description adds the defaulting behavior when product_id is omitted (return all products), which the schema does not state.

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 (season window), scopes it geographically and commercially (South African export), and specifies the representation (ISO weeks/months). It does not explicitly contrast itself with siblings like get_specs or list_products, which is the only thing keeping it from 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?

"Omit product_id for all products" gives clear conditional guidance on when to use the tool in broad vs. narrow form, and the schema points at list_products for valid ids. It stops short of naming an alternative tool or any exclusions, so it is clear context rather than full when/when-not routing.

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?

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real behavioral context that those annotations cannot express: every value is labelled Fact or Inference with sources, and traded count ranges plus some cartons are still pending, warning the agent that the payload is partially incomplete.

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 with no filler: the data inventory comes first and the data-quality caveat is placed last where it belongs. The opening is a verbless noun fragment, which makes it slightly harder to parse than it needs to be, but every clause carries information.

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 single-parameter read tool with no output schema, the description goes unusually far by naming the return fields and flagging incomplete data. The remaining gap is the relationship to siblings, particularly that product_id must come from list_products, which the description leaves to the 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?

There is one parameter with 100% schema description coverage ('Product id from list_products'), so the schema already carries the semantics. The description's 'for a product' merely confirms the scope and adds no format, validation, or sourcing detail 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 enumerates exactly what the tool returns for a product (cultivars, origin regions, grade classes, size codes, carton units, pack codes), which is concrete and far beyond a restatement of the name. It is framed as a bare noun list with no verb, and it draws no boundary against siblings like list_products or get_season, 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 phrase 'for a product' implies the tool is a per-product lookup, but there is no explicit when-to-use, no prerequisite statement (e.g. obtain product_id via list_products first), and no mention of when another sibling is preferable. An agent must infer everything about routing and sequencing.

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?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety and determinism profile is covered structurally. The description adds modest value by bounding the data domain ('no prices or volumes'), but says nothing about pagination, caching, or completeness of the category set.

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 primary purpose and followed by the two most useful disambiguators (reference vs. stock data, no prices/volumes). Every clause earns its place with no repetition of schema or annotation content.

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-parameter, read-only listing tool with no output schema, the description supplies everything needed: the domain (South African fresh fruit categories), the fields returned (HS heading and origin), and the boundary of the dataset. Nothing required to call it correctly is missing.

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?

The tool takes zero parameters, so per the rubric the baseline is 4. The description correctly implies there is no filtering or query input, and adds descriptive meaning about the returned fields (HS heading, origin) rather than leaving the agent guessing.

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 ('List the South African fresh fruit categories') and scopes it as reference data with HS heading and origin. The negative clarifier 'not a stock list' prevents a plausible misreading, though the siblings (contact_route, get_season, get_specs) are unrelated enough that no sibling differentiation is required.

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 only implied: 'reference data, not a stock list' tells the agent this is not for live inventory/pricing queries, but there is no explicit when-to-use statement or named alternative for questions about seasons or specs covered by siblings.

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