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 read-only, whether results span the whole SDK or a scoped subset, whether results are paginated or ranked, or how large the response is. Only the name hints at a read operation.

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?

The single line is short but that brevity is under-specification, not economy. The front-loaded content duplicates the name rather than telling the agent anything new, so no sentence earns its place beyond the platform scoping.

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 search tool with no output schema and no annotations, the description should at least characterize what comes back (reference entries, snippet format, how the agent should consume results). None of that is present, leaving the agent unable to predict the shape or usefulness of the response.

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?

One parameter with 100% schema description coverage ('Search terms for bundled SDK references'), so the schema already documents syntax, type, and the 500-char limit. The description adds nothing about query semantics (matching behavior, ranking, multi-term handling), so the baseline 3 applies.

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 a tautology: it restates the tool name 'api.reference.search' plus a hyphenated echo of it. It conveys only that this is a reference search for the Android flavor of MediaSFU, which the fully-qualified name 'android::api.reference.search' already carries. No distinct verb+resource statement beyond the name.

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?

No when-to-use guidance whatsoever. With ~13 sibling tools per platform (feature.map, fix.suggest, sdk.recommend, runtime.diagnose, etc.), the agent receives no signal about when a bundled-SDK reference lookup is the right choice versus those alternatives. Usage is left entirely to inference from the name.

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