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. It does not say whether the tool is a read-only lookup, whether it consumes requestedFeatures to rank recommendations, what the recommendation output looks like, or any prerequisites — only the alias keywords are given.

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 a single compact line with no filler sentences, so it is not bloated. However, the brevity comes from omission rather than discipline — the token that carries real information ('advisor') is buried after a path-like prefix.

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 tool with no output schema, no annotations, and two loosely documented parameters, the description supplies nothing an agent needs in order to invoke it correctly. The alias list helps keyword matching but does not make the definition complete.

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 description coverage is 50% and the covered half is trivial ('Application type.', 'Required feature.'). The description adds no meaning beyond the schema — it never mentions appType or requestedFeatures, nor how they shape a recommendation, so the uncovered/inferred semantics stay undocumented.

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?

The description is essentially the tool's own name plus a platform qualifier ('MediaSFU Apple / Swift :: sdk.recommend (advisor)') and a set of alias keywords. '(advisor)' hints at an advisory/selection role, but no verb+resource statement says what it actually does or returns, so it reads as a restatement of the name rather than a purpose.

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 at all. With ~140 siblings, many sharing the identical '::sdk.recommend' suffix across platforms (android::sdk.recommend, unity::sdk.recommend, shared::sdk.recommend) and adjacent tools like swift::integration.plan or swift::feature.map, the agent gets no condition for choosing this tool over them.

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