list_active_regions

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

Annotations already declare readOnly, idempotent, non-destructive behavior, so the safety profile is covered. The description adds genuinely new context beyond that: entries vanish one name at a time as region_end closes them, and state is per-bridge-instance and non-persistent across restarts. That is meaningful lifecycle detail, though it stops short of things like concurrency or rate behavior.

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?

Front-loaded with the core identity, then use cases, then lifecycle caveats, then a compact return-shape block. Every sentence carries information; no 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?

With no output schema, the description supplies the return shape ({ total, regions:[{name, started_at_s, elapsed_s}] }) so the agent knows what it gets back. Zero params, clear sibling routing, and state-persistence caveats make it fully self-sufficient for a no-argument 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?

Zero parameters, so per the rubric the baseline is 4. There is nothing to document, and the description instead previews the return shape, which is a useful substitute.

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?

States a specific verb+resource (the named timing regions still OPEN) and immediately positions itself relative to siblings as 'the read-side of region_start', with region_end named as the closer. An agent can distinguish it from region_start/region_end without opening a schema.

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?

Gives two explicit use cases ('spot a region you forgot to close' or 'read an elapsed time without ending the region') and contrasts with the closing alternative. Nothing about when to reach for this tool is left to inference.

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