Trades flagged as a potential conflict (company sector overlaps the official's committee or agency). Accepts branch/role/since/until filters.
| Name | Required | Description | Default |
|---|---|---|---|
| role | No | ||
| limit | No | ||
| since | No | ||
| until | No | ||
| branch | No | Either "congress" or "executive" (case-insensitive) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds context beyond annotations by explaining the conflict logic (company sector overlaps official's committee or agency). This clarifies the filtering mechanism. No contradiction with readOnlyHint or idempotentHint.
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 with two sentences: first states purpose, second lists filters. No filler text. Front-loaded with core functionality.
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?
While it explains the conflict criterion and mentions filters, it lacks details on return format, pagination, response structure, or how filters interact. Adequate for a read-only list tool but missing behavioral expectations.
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?
With only 20% schema description coverage (only branch has details), the description lists four parameter names (branch, role, since, until) but omits 'limit' and lacks any semantic detail beyond the names. This does not compensate for the schema gaps.
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?
Clearly states the tool lists trades flagged as potential conflicts due to sector overlaps. The description is specific and differentiates from siblings like list_recent_trades or search_trades by focusing on conflict status. However, it could be slightly more explicit about the verb (e.g., 'list').
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?
No guidance on when to use this tool versus alternatives like search_trades or list_recent_trades. The description only mentions accepted filters but does not indicate context, prerequisites, or 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.
Each tool targets a distinct operation: aggregates provides summary stats, search_trades for general search, list_recent_trades for recent entries, get_person_trades by individual, get_ticker_activity by ticker, and list_conflicts for flagged conflicts. No overlapping functionality.
All tool names follow a consistent verb_noun pattern using snake_case: list_ for listing, get_ for retrieval, search_ for searching, and aggregates as a descriptive noun. No mixing of conventions or inconsistent verbs.
With 6 tools, the server is well-scoped for a trades disclosure API. Each tool covers a core operation (search, list recent, by person, by ticker, conflicts, aggregates) without being excessive or sparse.
The tool set covers primary read operations and provides filtering via shared parameters. Minor gaps include no explicit 'get single trade by ID' or a tool to list available branches/roles, but the core workflow is well-supported for typical queries.
