Ungated, plain read of one worker row: name, contact, org, points, streaks, timestamps. (tascan_get_worker_passport is the rich stats view; this is the boring lookup.)
| Name | Required | Description | Default |
|---|---|---|---|
| worker_id | Yes | Worker ID |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds 'Ungated' meaning no special access controls, and 'plain read' clarifying it returns basic fields rather than computed analytics. This goes beyond annotations by specifying the ungated nature and the limited scope of data.
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 a single, well-structured sentence that conveys purpose, scope, and sibling differentiation with zero wasted words. It is front-loaded with the most critical information: 'Ungated, plain read of one worker row'.
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 the tool has only one required parameter and no output schema, the description is nearly complete. It tells the agent what the tool does, what fields it returns, and how it differs from a rich stats sibling. A small gap is that it doesn't specify what happens if the worker_id doesn't exist (e.g., error or null), but this is minor for a read 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% (one required parameter worker_id with a description). The description does not add parameter-level detail, but with only one parameter and full coverage, the baseline is 3. It earns a 4 by naming the specific fields returned (name, contact, org, points, streaks, timestamps), which helps the agent understand the output shape without an output schema.
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 states this tool reads a single worker row and enumerates the fields returned (name, contact, org, points, streaks, timestamps). It also contrasts itself with tascan_get_worker_passport, which provides the 'rich stats view,' making the purpose distinct from a sibling tool.
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 calls out that this tool is 'Ungated, plain read' and contrasts it with tascan_get_worker_passport ('the rich stats view; this is the boring lookup'), giving the agent clear when-to-use and when-not-to-use 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 map to a distinct resource+action pair, and the descriptions clearly separate entities like tasks, subtasks, workers, invoices, zones, assets, and reports. A few close pairs (get_report vs generate_report, dispatch_instruction vs dispatch_to_agent, analyze_issue vs auto_resolve) require careful reading, but the descriptions are detailed enough to disambiguate them.
The vast majority follow a tascan_verb_noun pattern with consistent create/get/list/update/delete verbs. Minor deviations like condition_history, server_info, zone_compliance, and one-word find slightly break the otherwise predictable pattern.
At 69 tools, this is far beyond what an agent can efficiently consider, and it bundles several distinct domains into one MCP surface. Even if each tool is individually useful, the combined set is an extreme mismatch for a coherent tool interface.
The surface covers nearly the full lifecycle for projects, events, tasks, subtasks, workers, reports, invoices, zones, assets, issues, and communications. Minor gaps exist (no explicit asset updates/decommissioning, no cancel_invite, no delete_zone), but the main workflows have no dead ends.
