StruXure NorCal Knowledge Base

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

No annotations are provided, so the description must carry the burden. It clearly discloses that it returns matching passages, not extracted answers, which is a key behavioral trait. It also implies the tool is read-only (answering a question) and sets expectations about output compatibility. This goes beyond mere purpose to explain the nature of the response.

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, concise and front-loaded with the primary purpose. It delivers the key distinction (returns passages, not answers) efficiently. No extraneous information. Slightly more could be added about typical use cases, but it is well-structured for its length.

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 retriever tool with no output schema, the description sufficiently explains what it returns (passages) and how it differs from a resolution provider. It lacks details on result format or ranking, but given the simplicity (2 params, no nested objects) and the clarity of operation, it is nearly complete. A minor gap is the absence of explicit search behavior (e.g., semantic search) or result ordering.

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 fully documents 'query' and 'topK'. The description does not add parameter-specific meaning beyond the schema, but it does clarify that 'query' is a natural language question and 'topK' controls result count. This is sufficient given the high schema coverage; the baseline of 3 is appropriate.

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 answers a question from FAQ content, specifies the action ('Answer a question') and the resource ('knowledge base's FAQ content'). It also distinguishes itself from the sibling 'troubleshoot' by noting the return type (passages vs. resolution), effectively differentiating it despite not naming 'troubleshoot' as a sibling in the given list.

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 to use by contrasting with 'troubleshoot' for broken items, but does not explicitly state 'use when the answer is informational' or 'when not to use'. It gives a clear context but lacks explicit exclusions or alternative selection criteria beyond the one example.

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 carries the full behavioral burden. It does disclose an important trait: the tool returns closest matches, not a complete list. However, it does not mention whether the operation is read-only, how it handles empty or poor matches, or what the result shape looks like.

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 entire description is one sentence that front-loads the core behavior and ends with a practical routing instruction. Every word earns its place, with no redundancy.

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 search tool, the description plus schema is nearly sufficient for an agent to select and invoke it correctly. The main gap is the absence of an output schema and any mention of edge-case behavior, but these are not critical for basic invocation.

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 `query` and `topK` are already documented. The description adds 'natural-language' framing, but this is largely reflected in the schema's own query description. No substantial extra parameter meaning is provided.

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: 'Find service offerings relevant to a natural-language query.' It also explicitly contrasts itself with `list_services` by saying it returns closest matches rather than a complete list, making its role clear.

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 clear usage context: use this tool for natural-language service search, and use `list_services` when a complete catalogue is needed. It does not explicitly address the `faq` sibling, but the domain difference is evident enough.

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