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

Goes well beyond destructiveHint=true by enumerating exactly what is destroyed (study plus membership list) and what survives and remains reachable by id and via mcg_list_runs. It also discloses the refusal conditions and the return payload (study_id, deleted, former_member_ids), which is the kind of consequence detail an agent needs before a destructive call.

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?

Four tight sentences, each load-bearing: what is deleted, what is not, when it is refused, and what is returned. Destruction scope is front-loaded before the caveats.

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?

Although there is no output schema, the description summarizes the return fields, and for a one-parameter destructive tool it covers ownership, side effects, refusal conditions, and recoverability. Nothing material is left for the agent to infer.

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 coverage is 100% and the single parameter is documented as a std_... id, so the baseline is met by the schema. The description adds meaning the schema does not: the study must be one the agent owns, which affects whether the call can succeed at all.

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 ('Delete a study you own') and immediately scopes the blast radius to the study and its membership list. This clearly differentiates it from siblings like mcg_get_study and mcg_archive, which suggest reading or softer lifecycle actions.

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?

Explicitly gives a precondition for use: refused while the study has documents or a live public link, with instruction to remove those in the app first. It does not name an alternative (e.g., mcg_archive) for the non-destructive case, so routing guidance is clear context but not full when/when-not coverage.

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