Ask SVV a bounded public question. Supported intents: capabilities, merchant_policy, merchant_trust and product_search. This tool never orders, negotiates, contacts people, takes payment or changes store data.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | ||
| intent | Yes | ||
| request_id | No | ||
| max_results | No | ||
| in_stock_only | No | ||
| max_price_eur | No | ||
| permission_scope | No | public_read |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. The 'never' clause discloses the tool's non-destructive, read-only nature, which is valuable. It does not mention rate limits, authentication, or error behavior, but for a simple query tool, this adds meaningful transparency beyond basic purpose.
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 wasted words. It front-loads the core purpose, then lists intents and constraints, achieving high information density.
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 has 7 parameters and no annotations, yet the description omits parameter semantics, usage alternatives, and edge-case behavior. While an output schema exists, the description leaves significant gaps for effective selection and invocation, especially given the 0% schema description coverage.
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 0%, and the description only lists supported intents without explaining parameters like query, max_results, in_stock_only, max_price_eur, or permission_scope. Even though the schema provides defaults, the description adds minimal semantic value beyond the intent values.
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 the specific verb 'Ask' with resource SVV, and clearly states the scope as a 'bounded public question' with supported intents. This distinguishes it from siblings like 'search' or 'fetch' by defining its exact querying role.
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 provides context by listing supported intents and explicitly stating what the tool never does (orders, negotiates, contacts people, takes payment, changes store data). However, it does not explicitly name alternative tools for when this tool should not be used, so it misses explicit exclusions.
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.
Some tools overlap in purpose: latest_memory_snapshot, ops_status_summary, and startup_operator_snapshot all provide some form of current state, and agent_query overlaps with search for information retrieval. However, the descriptions clarify distinct intents (e.g., bounded vs. full document search, operational vs. canonical snapshot), so boundaries are mostly clear.
All tool names use lowercase snake_case, but they do not follow a consistent verb_noun pattern. Some names are single verbs (fetch, search) while others are noun compounds (latest_memory_snapshot, ops_status_summary). This mixed style is readable but not predictable.
With 7 tools, the set is well-scoped for a public-facing query and status facade. Each tool serves a distinct role (query, search, fetch, snapshots, status, self-check), and the count feels appropriate without excess or deficiency.
The tool set covers the core needs of a read-only public facade: asking questions, searching documents, fetching content, and retrieving status/snapshots. There is some redundancy among snapshot tools, but no major missing operation for the stated purpose.
