Flush MCP Response Cache

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

Annotations already declare idempotent=true, destructive=false, readOnly=false. The description adds genuinely non-redundant context: the 'Side effects: Next reads refetch from the engine' note and the scope clarification that only the MCP cache, not the engine cache, is affected — critical for avoiding a destructive-looking mistake.

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?

Four labeled single-line sections, front-loaded with purpose and scope before side effects. No filler; every line carries distinct information.

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 parameterless maintenance tool with no output schema, the description covers scope, trigger, return expectation ('Confirmation'), and side effects — everything needed to invoke it correctly. No annotations are repeated or contradicted.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate. Baseline 4 applies; no parameter-level gaps exist.

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 verb (clear/flush) and resource (MCP process response cache), and explicitly disambiguates from the similarly-named FortiMail Engine server cache, which no sibling covers. An agent can immediately distinguish this from engine.status.

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?

Gives an explicit trigger: 'When reads look stale after changes made elsewhere.' It does not name alternative tools or when-not to use it, but the condition is concrete enough to select the tool reliably.

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