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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, so the safety profile is covered. The description adds genuine value beyond that by disclosing the response shape: per-pick cited facts (fits, gaps, ruled-out must-haves) plus a follow-up question, which tells the agent what to expect back without an output schema.

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?

A single front-loaded sentence that packs the action, the input, and the output contract with no filler. Every clause earns its place.

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?

With no output schema, the description does the work of explaining the return contents, and annotations cover the safety profile. Minor gap: it doesn't say how many recommendations come back or what happens when nothing matches the must-haves.

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?

Only one parameter, fully documented in the schema with a concrete example. The description's 'plain-language request' framing adds a useful hint that free-form natural language, including constraints like SSO or price, is expected rather than keywords.

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 ('Ranks') and resource ('apps in the AppFinder directory') with the input shape ('plain-language request'). This clearly separates it from keyword-oriented siblings like search_apps and from compare_apps/find_alternatives, which don't produce ranked recommendations with rationale.

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?

The phrase 'plain-language request' implicitly signals the natural-language recommendation use case versus keyword search, but the description never names an alternative or states when-not to use it. No prerequisites or exclusions are given, leaving sibling routing to inference.

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