project_force_stop

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

With no annotations, the description carries the full burden. It usefully discloses the confirm gate, the fingerprint safety guard, and the "never blind-kills" policy, which is real behavioral value. It omits what happens when the fingerprint does not match (refusal? error?), what signal is sent, permission requirements, and any timeout 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?

Three short clauses with zero filler, and the core action plus the confirm gate are front-loaded. The clipped, telegraphic phrasing ("never blind-kills") sacrifices a little clarity but not much space.

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, no-annotation, no-output-schema mutation tool with an undocumented timeout parameter, the description covers the headline safety story but leaves the failure modes and parameter semantics unaddressed. Enough to call it, not enough to call it confidently.

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 only 33% — only confirm is documented, and the description merely restates its required value. projectId and, more importantly, timeoutSeconds are explained nowhere; an agent has no idea what the timeout governs (kill deadline? fingerprint recheck window?) or its units and bounds.

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?

The description gives a specific verb+resource (stop a managed process) and adds a distinctive mechanism — the cmdline fingerprint guard — that separates it from a plain stop. It never names project_stop, however, so the agent must infer that this is the forceful variant of an existing sibling.

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?

"when cmdline fingerprint still matches" and "Allowed for unknown status" imply the conditions under which this tool is valid, but they are preconditions rather than explicit routing guidance. There is no statement of when to prefer this over project_stop or project_restart, which are direct siblings in the same list.

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