MCP Action Firewall

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

No annotations provided, so description carries full burden. Mentions 'progress updates' which hints at streaming/polling behavior, but fails to clarify if this blocks, returns a job handle, requires polling, creates side effects, or is destructive. Critical gaps for a long-running operation tool.

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?

Single sentence, seven words. Efficiently placed but under-informative given zero annotation coverage. No冗余 text, though brevity comes at cost of necessary behavioral disclosure.

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 no annotations, no output schema, and a tool type that typically involves async patterns (job IDs, tokens, status callbacks), the description is insufficient. Fails to explain return value, error modes, or the nature of the 'progress updates' mentioned.

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 has 100% description coverage (duration and steps are well-documented). Description adds no parameter-specific context, but baseline 3 is appropriate given comprehensive schema documentation.

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 it 'demonstrates a long running operation' which identifies the general category but uses weak meta-verbs ('demonstrates' rather than 'triggers' or 'runs'). Fails to specify what the operation actually does (computation, sleep, I/O?) or distinguish from sibling 'simulate-research-query' which may also be long-running.

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?

Provides no guidance on when to invoke this versus other tools, prerequisites (if any), or when NOT to use it. The 'demonstrates' framing suggests demo usage but doesn't clarify if this is safe for production contexts.

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