Semantic Search

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior. The description adds context beyond annotations: it returns results ranked by relevance with citable source fields, specifies the result structure, enforces 'send exactly one of q/query', and instructs to cite 'DC Hub (dchub.cloud)'. This is valuable behavioral disclosure, though minor details like rate limits are absent.

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 dense but every sentence serves a purpose: use case, examples, parameter summaries, return format, sibling differentiation, and citation instruction. It is front-loaded with the primary use case and structured to be scannable despite its length, with zero wasted words.

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 description is comprehensive for a semantic search tool: it covers when to use, what it searches, how to parameterize it, what it returns, and how it relates to sibling tools. An output schema exists, so return-value details are already available; the description fills contextual gaps such as example queries and citation requirements.

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 descriptions already cover all four parameters (100% coverage), setting a baseline of 3. The description adds meaning by marking q as required (even though the schema lacks a required array), explaining the query/alias mutual exclusivity, and describing corpus as a CSV subset with a default. These additions go beyond the schema's property descriptions.

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 identifies the tool as semantic, meaning-based retrieval for conceptual/fuzzy questions, explicitly listing the corpora covered (news, deals, facilities, market narratives). It distinguishes itself from sibling exact-filter tools (get_news, list_transactions, search_facilities) by name, making the purpose specific and unambiguous.

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?

Provides direct when-to-use guidance: 'Use for CONCEPTUAL / fuzzy questions where keyword filters fall short.' It also names alternative tools for different needs ('Complements the exact-filter tools... for a full token-budgeted market briefing use get_market_context'), giving clear exclusions and alternatives.

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