search_public_knowledgeSearch the approved public pages of Helena Bioinformatics and its products. Return source-cited evidence.
| Name | Required | Description | Default |
|---|---|---|---|
| site | No | all | |
| history | No | ||
| language | No | ||
| question | Yes | ||
| request_id | No |
| Name | Required | Description | Default |
|---|---|---|---|
| protocol_metadata | Yes | ||
| canonical_response | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds meaningful context about the search scope ('approved public pages') and the nature of results ('source-cited evidence'), enhancing transparency beyond the structured annotations.
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 concise (two sentences), front-loaded with the action verb 'Search,' and every sentence contributes meaning. It is appropriately brief but could be slightly more informative about scope or parameters without becoming verbose.
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?
Given the tool has 5 parameters, including the important 'site' enum, and no parameter descriptions, the description is somewhat minimal. However, the presence of an output schema and annotations mitigate the need to explain return values or safety. The description covers the tool's core purpose but leaves the site/filtering and history behavior unexplained.
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 input schema has 5 parameters with 0% description coverage, and the tool description provides no details about any of them (site, history, language, question, request_id). The description fails to compensate for the schema's lack of field descriptions, leaving parameter semantics 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?
The description clearly states the tool searches 'approved public pages' and returns 'source-cited evidence,' providing a specific verb, resource, and output type. It distinguishes from the sibling 'ask_public_knowledge' by emphasizing search over asking, though it does not explicitly name the alternative.
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 usage by defining what it does ('search approved public pages') and its output ('source-cited evidence'). However, it provides no explicit guidance on when to use this tool instead of the sibling 'ask_public_knowledge' and does not mention exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct purpose: ask_public_knowledge answers questions, search_public_knowledge retrieves cited evidence, and support_helena handles a separate opt-in action about supporting Helena. No overlap or ambiguity between them.
All tools follow a consistent verb_noun pattern: ask_public_knowledge, search_public_knowledge, support_helena. The style is uniform and intuitive, making the set predictable.
Three tools is a well-scoped count for a knowledge-answering server. Each tool earns its place: one for querying, one for searching, and one for a distinct support action. No bloat or thinness.
The server's purpose is to provide answers from public knowledge with citations. The ask and search tools cover the core workflows fully, and the support tool addresses a separate but relevant action. No obvious gaps in the domain.