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

No annotations are provided, so the description carries the full behavioral burden, and it discloses nothing: no indication of whether this is a read-only advisory call, whether it mutates project state, what inputs it requires, or how expensive/remote the operation is. "(advisor)" is the only behavioral hint, and it is not elaborated.

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?

It is one terse line with zero front-loading problems, but the brevity is under-specification rather than economy — almost no informational content for a tool with two inputs and no output schema.

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 recommendation tool with no output schema and half its parameters undocumented, the description should at minimum explain what a recommendation consists of and how appType/requestedFeatures shape it. None of that is present, leaving an agent unable to know when or how to call it.

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 50% and the existing schema text is thin ("Application type.", "Required feature."). The description adds no meaning to appType or requestedFeatures — no accepted values, no format examples, no effect on the recommendation. With low coverage the description should compensate, and it does not.

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?

"MediaSFU Android :: sdk.recommend (advisor)" restates the tool name with a platform prefix and an ambiguous parenthetical. "advisor" hints at guidance/recommendation, but there is no verb+resource statement of what is actually returned or recommended (an SDK package? a config? a version?). An agent cannot distinguish this from sibling shapers like android::ui.mode.recommend or android::integration.plan without guessing.

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?

There is no when-to-use guidance, no prerequisites, and no named alternative among the many sibling planner/recommender tools. The runtime sibling pattern (ui.mode.recommend, integration.plan, feature.map) makes routing ambiguous, and the description does nothing to resolve it.

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