MCP Action Firewall

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

With no annotations provided, the description carries the full burden of disclosing side effects, return format, and content structure. It fails completely—the word 'demonstrates' suggests read-only behavior but doesn't confirm return values, content lifecycle, or what 'annotated' metadata actually looks like in the output.

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?

While brief (one sentence), it front-loads meta-commentary rather than functional purpose. The sentence doesn't earn its place because it fails to describe the tool's actual operation or value proposition.

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?

Given the lack of output schema and annotations, the description should explain what the tool returns (an annotated message with what structure?) and what the 'annotation patterns' mentioned actually entail. It leaves critical gaps for a tool with no other behavioral metadata.

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?

Description adds no information about parameter semantics beyond the schema. However, the schema has 100% coverage with clear descriptions ('Type of message...', 'Whether to include...'), so baseline 3 is appropriate. The description doesn't contextualize why one would choose 'error' vs 'success' or what the 'example image' represents.

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 states 'Demonstrates how annotations can be used...' which describes a pedagogical/meta-purpose rather than what the tool actually does functionally (retrieve a message). It fails to specify what 'annotated message' means in this context or what the tool returns, leaving the agent unclear whether this is a demo utility or a functional message retrieval tool.

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 select this tool versus siblings like 'get-structured-content' or 'echo'. No mention of prerequisites, error handling, or when the specific messageType values should be used.

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