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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false. The description adds genuinely new behavioral context beyond those: the output is deterministic and delivered as base64, and no external state changes. It stops short of noting whether compile is expensive or what errors look like for invalid blueprints.

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?

Two short sentences with no filler; the output format is stated up front and the non-publishing constraint follows it. Every clause earns its place.

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 output schema, the description correctly supplies the return shape (base64 ZIP) and determinism, and it clarifies the tool's non-mutating nature. The remaining gap is the undocumented blueprint object, which is the one thing an agent most needs to call it correctly.

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?

There is one required parameter (a nested object) with 0% schema description coverage, so the description must carry the load. It only says 'valid blueprint' and never characterizes the object's expected fields or structure, leaving the agent to guess at the most important input in the call.

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 (compile), a specific input (valid blueprint) and a specific output form (deterministic ZIP as base64). The phrase 'does not publish the plugin' implicitly distinguishes it from sibling tools like preview_plugin or any publish path, so an agent can place it accurately.

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?

Implies usage via 'a valid blueprint', which hints validation should precede compilation, but never names validate_blueprint or preview_plugin as alternatives or states when to prefer this tool over them. Usage is inferable but not explicit.

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