stop_build

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

With no annotations, the description carries the full burden and does so well: it flags destructiveness, the resulting ABORTED state, that completed work is lost, the mode escalation semantics, and the three required environment flags (MCP_ALLOW_BUILD_WRITE, MCP_ALLOW_DESTRUCTIVE, MCP_ALLOW_BUILD_STOP).

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 one-line summary followed by tightly packed constraints; every sentence adds operational information with no filler.

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 mutation tool with no annotations and no output schema, the description covers effects, preconditions, and mode behavior well. Minor gaps remain, e.g., behavior when the build is already finished or per-job permission nuances.

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 0% and the schema gives mode only a default, so the description must compensate. It thoroughly explains mode (escalation and build-type restrictions), which is the non-obvious parameter; job_name and build_number are obvious by name but left undocumented.

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 in the first line: 'Stop a running build.' Clearly distinguishes itself from siblings like trigger_build, get_build_info, and cancel_queue_item.

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?

Explains the mode escalation path (stop -> term -> kill) and the key constraint that Freestyle builds support only stop while term/kill are Pipeline-only and require workflow-job. It does not explicitly compare against siblings such as cancel_queue_item, so it stops short of a full routing guide.

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