delete_experiment

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

With no annotations provided, the description carries the full burden and does it well: it declares irreversibility, explains exactly what is destroyed (the Experiment and its results), and explicitly what survives (sessions it reused, replays, scoring runs). It also states the return shape ("a confirmation, or an error message").

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 action and its immediate consequence, with no wasted sentences. The Sphinx-style ":param"/":returns:" markup reads as raw docstring artifacts rather than agent-facing prose, which slightly hurts readability.

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 zero annotations and no output schema, the description covers destruction scope, data retention, the confirmation requirement, and return shape — enough to call it safely. Missing pieces are permission/auth requirements, the id's provenance, and error conditions such as a nonexistent experiment.

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%, so the description must compensate, but ":param experiment_id: The Experiment's id" only restates the parameter name. For a destructive one-parameter tool, it should say where the id comes from (e.g. list_experiments/get_experiment) or its format, since a wrong id is unrecoverable.

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 and resource ("Deletes an Experiment and its results") and adds scope detail about what is and isn't removed. It is unambiguous against the many experiment siblings, but it never explicitly names an alternative or contrast tool, so it stops short of full sibling differentiation.

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?

"This cannot be undone: get a yes first" establishes a hard precondition (user confirmation) before calling, which shapes when the tool should be used. There is no routing guidance toward alternatives such as update_experiment or archiving, and no guidance on when deletion is unnecessary.

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