eda_session

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds the important behavioral instruction that the returned target must be used unchanged on subsequent tools, which goes beyond the annotations. It does not disclose what the target looks like or how "bridge" behaves, but it does not contradict the 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 a single sentence split into two concise clauses: what the tool inspects and how to use the result. No words are wasted, and the functional instruction is placed at the end where it completes the purpose. It is appropriately sized for a simple, low-parameter tool.

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?

With only one optional parameter, no output schema, and strong safety annotations, the definition is adequate for basic invocation. Still, the meaning of "bridge," the effect of windowId, and the shape or contents of the returned target are left vague, which makes the description incomplete for an agent that must reliably pass the target to later tools.

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 schema has one optional parameter, windowId, and schema description coverage is 0%, so the description carries the burden of explaining it. The description never mentions windowId, what it filters or selects, or how it affects the returned target. This is a significant gap for an agent deciding whether and how to populate the parameter.

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 uses the concrete verb "Inspect" with a clear resource list—bridge, windows, active project, document, and boards—so an agent can tell this is a session/context introspection tool. It also explains that a target is returned for reuse, which helps distinguish it from more focused state tools like sch_get_state and pcb_get_state. However, "bridge" is unexplained jargon, and the exact relationship between the returned target and the inspected items is left implicit.

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 instruction "Use returned target unchanged on subsequent tools" gives clear usage guidance: call this tool first, then pass the returned target to later tools without modifying it. This is practical and actionable. It does not explicitly name alternatives or say when not to use this tool, but the context strongly implies it is the session-entry tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.