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

Annotations already declare destructiveHint=true and openWorldHint=true, so the description only needs to add context. It does add one useful constraint — you can only remove cells you own or published — which is not encoded anywhere in the schema. Still, the truncated sentence leaves unclear what the removal scope is (e.g., are published artifacts/community listings taken down too?).

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 and dense, with no wasted words in the visible portion. However the description ends mid-sentence ('; a...'), which is a structural defect that leaves the reader with an unfinished thought.

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 destructive, non-idempotent, open-world mutation with no output schema and 0% param docs, the description does cover ownership and parameter meaning. It stops short of the things an agent most needs before a destructive call: consequences of stopping (does the cell/data survive?), and behavior when neither param is supplied (required params = 0).

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 carry both params — and it does, mapping `name` to your hosted cell and `cell` to a community cell you published. That is real semantic value the schema does not supply, though it never says whether the params are mutually exclusive or whether both can be passed.

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?

Specific verb+resource ('Stop and remove your own hosted cell') with the two addressing modes spelled out — `name` for a cell you host, `cell` for a community cell you published. That distinguishes it cleanly from siblings like host_stop and cell_publish 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?

The ownership qualifier ('your own', 'you published') implicitly scopes when it applies, and the two address modes hint at which to pick. But no explicit when-not, no named alternative for non-owned cells, and the trailing clause is cut off so any further guidance is lost.

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