hardware_compare_robotsCompare 2 to 5 robots side by side on semiconductor BOM, metrics, risk and geographic exposure. Requires an access right on EVERY robot listed; if one is missing the call returns a refusal naming it, and compares nothing.
| Name | Required | Description | Default |
|---|---|---|---|
| robot_ids | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds significant behavioral context beyond the annotations: it explains the access-right requirement and the exact failure behavior ("if one is missing the call returns a refusal naming it, and compares nothing"). This is richer than the readOnlyHint and destructiveHint, which are already covered. There is no contradiction with 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?
The description is two sentences, with both sentences providing essential information—purpose first, then requirement and failure. Every word adds value; no redundancy or filler.
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 tool with one parameter and no output schema, the description covers purpose, domain, requirements, and failure mode. It is fairly complete, though it could be slightly more explicit about the output format (e.g., what the comparison result looks like). However, given the simplicity and the presence of sibling tools, it strikes a good balance.
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?
The description provides some meaning for the 'robot_ids' parameter by indicating it should contain IDs for 2 to 5 robots, but it does not specify the format (e.g., comma-separated string, JSON array). With 0% schema description coverage, the description partially compensates but leaves ambiguity about how to supply the IDs.
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 explicitly states the tool's function: "Compare 2 to 5 robots side by side on semiconductor BOM, metrics, risk and geographic exposure." It specifies the verb (compare), resource (robots), and a distinguishing scope (semiconductor), which differentiates it from sibling tools like mechanical_compare_robots and software_compare_robots.
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 clearly implies the domain of use via 'semiconductor' in the description, distinguishing it from mechanical and software compare tools. It also states a concrete prerequisite: "Requires an access right on EVERY robot listed." However, it does not explicitly tell the agent when not to use it or recommend an alternative for other domains, stopping short of being fully explicit.
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.
The layer prefixes and action verbs make most tools clearly distinct, but the three list_robots variants return the same catalogue and the three get_robot variants share identical commercial fields, creating real selection ambiguity. The descriptive warnings like 'call one, not three' help but do not fully resolve the overlap.
All 27 tools follow a uniform <layer>_<action>_<object> snake_case pattern with consistent verbs: get, list, compare. There are no mixed naming conventions or stylistic deviations.
27 tools is above the comfortable range and is inflated by triplication: list_robots, get_robot, compare_robots, list_signals, and system_status are repeated across layers with only minor differences. A layer parameter could consolidate a large portion of the surface without losing functionality.
As a read-only intelligence platform, the set covers catalogue listing, comparison, robot profiles, BOM details, block analysis, dependency analysis, signals, and system health across hardware, mechanical, and software layers. The main gap is the lack of a consolidated multi-layer robot view, though agents can compose one from the three get_robot variants.