workFetch full details for one Trove item by id — a Trove work id (from search). Requires your own free Trove API key, passed as _apiKey.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | e.g. "12345". | |
| _apiKey | Yes | Your own Trove API key (BYO — Pipeworx does not supply one). Free at trove.nla.gov.au: create an account, then Create an API key. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds the key behavioral need not visible in annotations: the agent must supply its own Trove API key via _apiKey. This is auth-related context that goes 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?
A single, front-loaded sentence states the purpose, the input source, and the key prerequisite. There is no filler or repetition of schema details, so every clause earns its place.
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 single-item fetch with no output schema, the description covers the essential context: what is returned ('full details'), how to identify the item ('work id from search'), and the auth requirement. It is slightly light on response-shape detail, but this is a minor gap given the tool's simplicity.
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 the baseline is 3. The description adds meaning to the id parameter by specifying it is a 'Trove work id (from search)', which the schema's terse 'e.g. 12345' does not convey. This slightly exceeds the baseline.
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 names a specific verb ('Fetch'), a specific resource ('full details for one Trove item by id'), and the exact id type ('a Trove work id'). This clearly distinguishes it from sibling search tools by scoping it to a single item 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?
It tells the agent the id comes 'from search', which implies the proper workflow without explicitly naming an alternative tool. It also states the API key prerequisite. This is clear usable guidance, though it stops short of explicitly saying 'use search first' or listing 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.
Several tools have overlapping purposes (e.g., ask_pipeworx, ask_pipeworx_grounded, deep_research all answer questions; entity_profile, compare_entities, recent_changes all cover company data). Descriptions provide distinctions, but an agent can easily misselect, especially between the Pipeworx query tools.
Tool names follow mixed conventions: some use verb_noun (list_subscriptions, unsubscribe), others use descriptive phrases (ai_visibility_check, polymarket_arbitrage) or nouns (deep_research, entity_profile). No consistent pattern, making it harder to predict tool names.
With 32 tools covering diverse domains (data lookups, prediction markets, memory, subscriptions), the server feels overloaded. The scope would be better served by splitting into smaller, focused servers (e.g., data query, prediction market, memory). Many tools are peripheral to a core purpose.
The tool surface is fairly comprehensive within its domains: CRUD for memory (remember/recall/forget), subscription management, extensive data query options, and prediction market analysis. Minor gaps exist (no update memory, no direct trading), but agents can work around them.