list_accountsAccounts and custody for the household.
| Name | Required | Description | Default |
|---|---|---|---|
| status | No | OPEN | |
| household_id | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already communicate readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is known. However, the description adds almost no behavioral context beyond 'custody' and 'household,' and does not disclose filtering behavior, defaults, or response semantics.
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 very short, but this is under-specification rather than meaningful conciseness. It is a bare noun phrase with no actionable verb, context, or parameter information, so the brevity does not serve the agent.
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?
Although an output schema exists and annotations cover read-only safety, the description leaves the tool's filter semantics and intended scope highly implicit. An agent cannot determine whether household_id is required, what status values are valid, or what kind of accounts are included beyond the vague 'custody' hint.
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 names neither status nor household_id. The default status value 'OPEN' and the meaning of household_id are left completely unexplained, so the description provides no help in understanding the parameters.
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 'Accounts and custody for the household' identifies a resource domain but uses no verb, so the action must be inferred from the tool name and title. It weakly hints at scope with 'household' and 'custody,' but does not clearly state what the tool does or differentiate it from sibling list tools.
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?
There is no guidance on when to use list_accounts versus list_households, list_documents, or other sibling tools. It also does not explain how the status or household_id parameters should be used to select between use cases.
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.
Most tools are distinct, but several pairs overlap in purpose: get_market_data and list_watchlist both return watchlist prices/signals, and the four 'brief' tools have fuzzy boundaries. Descriptions help, but an agent could easily select the wrong one without deeper context.
The dominant verb_noun pattern (get_* for details, list_* for collections) is clear and consistent in style. There are minor deviations like lookup_index_by_brand and run_technical_analysis, and several plural collections use get_, but these remain readable and mostly predictable.
39 tools is well past the 25+ threshold and represents a heavy surface for an agent to navigate. The broad wealth domain explains some of the count, but many granular getters could be consolidated or curated.
The set covers the advertised wealth surface well—portfolio, risk, credit, real assets, markets, geopolitics, watchlist, goals, family, and documents—but it is read-only and lacks obvious navigation endpoints like list_portfolios or detail views for goals/alerts. Agents can retrieve most data, but not all lifecycle operations or entity enumerations are present.