exp_status

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

The annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. Beyond that, the description discloses the live-versus-persisted behavior depending on session age, which is non-obvious context an agent could not get from the schema or 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?

Two sentences, no waste, and the primary behaviour (live state of a running experiment) is front-loaded before the earlier-session caveat. Every clause carries information.

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 read-only status tool with annotations covering safety and an output schema covering return shape, the description supplies the remaining essentials: what state is reported and how older experiments behave. Only the parameter's identity is left unaddressed.

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 description coverage is 0% and the only parameter is a bare 'name' string with no explanation in either schema or description. With a single parameter the ambiguity is limited, but the description contributes nothing about what name identifies (experiment vs run), so it fails to compensate for the coverage gap.

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 resource (experiment) and what is returned: the live state of a running experiment, enumerated as planned/done/failed, level, ETA, last error, recording ids. This clearly separates it from exp_list and exp_get in intent, though it never names a sibling to sharpen the boundary.

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?

It draws a useful internal distinction between a currently running experiment (live state) and one from an earlier session (persisted status), which is genuine usage guidance. However it never routes the agent to alternatives such as exp_get or exp_runs, so the choice among experiment tools 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.