Did the founder finish connecting the growth data source you handed them a link for? Pass the poll_token start_connection returned. Reports pending (wait poll_after_seconds and ask again), connected, expired (mint a fresh link) or not_found. Idempotent: nothing is spent or consumed. Read-only, free.
| Name | Required | Description | Default |
|---|---|---|---|
| poll_token | Yes | The poll_token start_connection returned. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations (readOnlyHint, destructiveHint), the description explicitly states 'Idempotent: nothing is spent or consumed. Read-only, free.' This adds important behavioral context about side effects and costs. It also enumerates all possible outputs, enhancing transparency.
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 front-loaded with a clear question and provides all necessary details in a compact form. It is somewhat conversational and slightly longer than necessary (e.g., the question format could be more direct), but every sentence contributes valuable information, so it earns a 4.
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?
Given no output schema, the description sufficiently covers the tool's behavior: it explains the input, all possible statuses (pending, connected, expired, not_found), and how to handle each (wait or re-mint). It also notes idempotency. This is complete for a read-only polling tool.
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% with the poll_token parameter already described as 'The poll_token start_connection returned.' The description repeats this same instruction without adding additional semantics, so it meets the baseline for full schema coverage but does not go beyond.
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 indicates the tool polls the status of a connection, using a question to frame the purpose ('Did the founder finish connecting...?'). It specifies the resource (growth data source connection) and reports statuses (pending, connected, expired, not_found), distinguishing it from siblings like start_connection and list_connections.
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 explicitly tells the agent to pass the poll_token returned by start_connection. It also provides actionable guidance for each status: wait poll_after_seconds and ask again for pending, mint a fresh link for expired. This is clear when-to-use and what-to-do guidance.
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 have clearly distinct purposes, and descriptions are thorough. A few pairs (e.g., ship_move vs set_output_status, dismiss_gap vs skip_move) overlap on the dismissal concept but operate on different surfaces, so an agent can usually tell them apart with careful reading.
All tool names follow the same snake_case verb_noun pattern (e.g., get_move, create_checkout, untrack_prompt). Retrieval tools consistently use get_ for single items and list_ for collections, and action verbs are precise, so the naming is fully predictable.
42 tools is heavy by any standard, exceeding the 25+ threshold in the calibration. While each tool may earn its place given the breadth of the domain, the sheer number will overwhelm an agent and complicate tool selection.
The tool set covers the main lifecycles well: moves (list/get/ship/skip/archive/undo/update), outputs (list/get/ship/redraft), connections (list/start/poll/disconnect), prompts (track/untrack/list), and scans (refresh/get/set intensity). Minor gaps exist, such as no direct edit for KB pages, but record_insight partially fills that.