Tangerine Index

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is fully covered elsewhere. The description adds one genuinely behavioral detail — the link-response status reflects the last check, implying cached/stale data — but the rest of the text is a return-field listing rather than operational context such as rate limits or missing-record behavior.

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 sentence, front-loaded with the action and identifier, then the payload. No filler, no repetition, and every clause adds a distinct field group.

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 a full output schema and complete annotations, the definition is sufficient to invoke the tool correctly. Minor inefficiency: the bulk of the text re-describes return fields already defined by the output schema rather than covering usage or failure behavior, though nothing an agent needs is actually 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?

Schema description coverage is 100% and the sole parameter is documented in-schema, including its 10-hex-character pattern and that ids come from search_products or similar_products. The description only restates 'by id' and adds no format or sourcing guidance beyond the schema, so the baseline 3 applies.

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 ('Get one product by id') and enumerates exactly what is returned. The phrase 'one product by id' implicitly contrasts with the list-style siblings search_products and similar_products, so an agent can tell it is a single-record lookup.

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: the reader infers this is the tool for expanding a single product once an id is known. It never explicitly says when to use it instead of search_products or similar_products, nor does it state prerequisites or error conditions for an unknown id.

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, closed-world, so the safety profile is covered. The description adds useful non-obvious context: relevance ranking is keyword + semantic, per-source reaction counts are never combined, and Tangerine Index does not rate products. That said, for a lookup tool most of this is result-shape detail rather than behavior an agent must know to call it correctly.

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?

Front-loaded with the purpose and usage trigger, with filters and ranking behavior following logically. The closing sentence describing the per-result shape is somewhat redundant given the output schema exists, so it is dense but not maximally lean.

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?

Covers the query semantics, ranking behavior, per-source number caveats, and hand-off to get_product, which is everything an agent needs given an output schema already exists. Nothing required to invoke 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?

Schema coverage is 100%, so all four parameters are already documented in the schema, including the example for `need` and the filter semantics of `forms` and `open_source`. The description reinforces the plain-English phrasing and the example query but adds little beyond what the schema already states; baseline 3 applies.

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 (find existing products) and adds a concrete scope the siblings don't share: products launched since Nov 30, 2022. It explicitly routes full-detail lookups to get_product, so an agent can tell it apart from siblings.

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?

Gives an explicit when-to-use trigger ('check here before building something new'), tells the agent how to phrase input ('describe the job in short plain English', English preferred), and names the alternative (get_product) with the condition that selects it.

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?

The annotations already establish read-only, idempotent, non-destructive, closed-world behavior. The description adds meaningful behavioral context beyond the annotations: the result cap of 5 and the fact that ranking is based solely on description embedding rather than quality, popularity, or recency.

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 tightly written sentences with no wasted wording. The core purpose and limit are front-loaded, followed by the important similarity caveat.

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 tool is simple, has a fully described single parameter, and includes an output schema, so the description does not need to explain return values. It is nearly complete, though it could explicitly state whether the input product itself is excluded from 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 description coverage is 100%, and the id parameter already explains that it comes from search_products or similar_products. The description adds only that the input product's description is used for matching, so it does not need to compensate for schema gaps.

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 uses a specific verb and resource ('List ... products'), states the limit ('up to 5'), and defines similarity precisely as description-embedding closeness. It also explicitly excludes quality, popularity, and recency, which sufficiently distinguishes it from sibling tools like search_products and get_product.

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 when the tool is appropriate by saying it finds products closest to a given product's description, and it clarifies what similarity does not mean. However, it does not explicitly state when to use this tool instead of search_products or get_product, so guidance is only implied rather than spelled out.

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