plugins_upload

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

Annotations already declare destructiveHint=true, but the description adds critical context the annotations can't: the refusal on existing IDs, the asynchronous scheduler-based apply, and that the tool cannot confirm liveness. This is exactly the kind of operational nuance an agent needs beyond the safety flags.

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?

Three compact sentences, front-loaded with the action and the refusal behavior before the replacement guidance and async caveat. No filler or repetition.

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 write tool with no output schema, the description covers what gets written (database), when it takes effect (scheduler later), what it cannot confirm (liveness), and the replacement workflow. Nothing an agent needs to avoid a bad call is missing.

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 100% and both parameters (files, method) are fully documented in the schema, so the description correctly defers to it. It adds no parameter-level detail itself, which is acceptable at this coverage level, but it doesn't earn extra credit.

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 and resource ('Install UI plugins from base64 archives') and immediately names a key constraint ('an existing plugin ID is refused'). An agent can distinguish this from plugins_list and plugin_delete without opening the schema.

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 names the alternative path for replacement ('Use plugin_delete first to replace a UI plugin') and the condition that triggers it (existing plugin ID). It also notes the failure mode when the ID exists, so the agent knows when not to call it directly.

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