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

Annotations already cover readOnly, idempotent, non-destructive, and closed-world, so the safety profile is set. The description still adds real behavior: three decision outcomes, an act cap of 5 items, the strict rule that service-only matches never appear, and fail-open degradation. However, it does not say what the payload looks like or how next_cursor is returned, leaving the consumption contract partly implicit.

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 call timing and the stack-change value proposition before the decision semantics and fail-open clause. It is dense but nearly every clause carries operational meaning; the single long paragraph and the clipped phrasing ("decision clear = ...") make it slightly harder to scan than it could be.

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?

With 9 parameters and no output schema, the description does the heavy lifting: it explains the first-call vs. subsequent-call contract and defines the three decision states and their item limits. Gaps remain around the undocumented models/services/installed parameters and the exact response envelope, but an agent could call it correctly from this text.

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 only 56%, but the description compensates well: it gives the package syntax ("npm:@modelcontextprotocol/sdk@1.9.0"), the runtime object example ({"node":"22"}), a features example ("tool_choice:any"), and explains the stack_fingerprint + cursor continuation loop. Models, services, and installed remain unexplained in both places, keeping it short of a 5.

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 action and resource: call once at session start to learn what changed since the last run that can break THIS stack, plus the required action. The decision vocabulary (clear/act/block) makes the output's purpose unambiguous and it is clearly distinct from the sibling lookup tools.

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 prescribes when to call (once at session start), the two-mode usage (send the full stack once, then just stack_fingerprint + cursor on later sessions), and when not to act on it (fail open: continue with the original task if Breakwire is slow, down, or empty; never block).

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