HortOS (New Zealand)

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

Annotations only cover safety flags (readOnlyHint=false, openWorldHint=true, idempotentHint=false), so the description must and does add real behavior: it returns priced lines plus a link to a priced list on HortOS that a human opens, checks and sends themselves, and it explicitly does not place an order. This human-in-the-loop model and the non-mutating-in-practice boundary go well beyond the annotation set, though it says nothing about failure modes when a line cannot be matched to a grower.

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 dense sentences: the first front-loads what is produced and the matching behavior, the second covers the return artifact and the workflow boundary. No filler and nothing repeated from the schema or annotations.

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 return-value burden and does so ('the priced lines and a link to the priced list'), plus the human follow-up step and the no-order boundary. Combined with 100% schema coverage and present annotations, an agent has everything needed to call it correctly.

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. The description adds a meaningful nuance beyond the schema by saying growers near the job are 'preferred' rather than required, clarifying that `near` is a soft preference and not a hard filter. It does not add format details beyond the schema's own example.

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 specific verb and resource ('price a whole plant list or planting schedule from wholesale growers' live stock lists') and scopes it to per-line matching of grower, size and trade price. It is clearly distinct from the one sibling (search_plants), though it never names that alternative to route the agent 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?

It establishes context (a plant list or planting schedule to be costed) and an explicit boundary ('This tool does not place an order'), so the agent knows this is pricing, not procurement. It stops short of naming when to prefer it over search_plants or any prerequisite for a successful run.

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 readOnlyHint and openWorldHint already declared, the description adds useful context: it returns grower availability, pot sizes, and NZD ex GST pricing, and accepts both botanical and common names. This goes beyond the annotations and helps set expectations for result scope, though it does not describe response structure or limitations.

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?

The description is two sentences with no filler. It front-loads the core purpose and immediately answers likely agent questions about what the search returns and how to phrase queries.

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 read-only search tool with a single required parameter and well-documented optional parameters, the description is sufficient to guide correct invocation. It covers purpose, query style, and key output dimensions. It could slightly improve by clarifying the relationship to price_plant_list, but this is not a blocking 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 description coverage is 100%, so the schema already documents all three parameters clearly. The description adds a useful note about botanical/common name flexibility, but does not substantially enrich the semantics of the size or state parameters 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 clearly states the tool searches New Zealand's live wholesale plant market, returning growers, pot sizes, and trade prices. It uses a specific verb and resource, making its purpose obvious. It does not explicitly differentiate from the sibling tool price_plant_list, but the purpose is specific enough.

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 gives concrete example queries ('who grows X' or 'what does X cost wholesale') and notes botanical or common names both work. It provides clear context for use, though it does not state when to avoid this tool or mention the sibling alternative by name.

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