install_plugins

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

Goes well beyond the supplied annotations: refusal of duplicate plugin IDs, error reporting for bad archives, persistence to the database, deferred application by the scheduler, and the explicit limitation that the tool cannot confirm the plugin is live. That deferred/async behavior and duplicate-ID refusal are exactly the kind of facts an agent cannot infer from readOnlyHint/destructiveHint.

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?

Front-loaded with the core action and input shape, and every clause carries information about format, refusal, or deferred execution. The telegraphic sentence fragments make it slightly harder to parse than flowing prose, but nothing is wasted.

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?

No output schema exists, and the description compensates by explaining what happens after the call (saved to DB, applied later, cannot confirm live). It is slightly silent on multi-file semantics and what a partial success looks like when some archives in the array are bad.

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 already 100%, so the baseline is 3; the description adds real meaning by stating the archive container formats and the plugin.json requirement, which the schema only hints at ('(.zip, .tar.gz or .tar.xz)'). It does not explain the 'method' parameter's only-valid value, though the schema description already covers that.

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') plus the exact input shape ('base64 archives {filename, content_base64}') and the accepted archive formats with the required plugin.json inside. An agent can distinguish this from uninstall_plugin and list_plugins without opening any 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?

Gives clear conditional guidance: an existing plugin ID is refused, so 'Uninstall first to replace' tells the agent the prerequisite for a re-install. It does not explicitly name list_plugins as the way to check for an existing ID beforehand, so the routing advice is implied rather than spelled out.

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