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

With no annotations, the description carries the full burden of disclosure and excels. It explains that 'sealed' apps cannot send data anywhere (browser-enforced), counts are real measurements (distinct days opened, installs), and there are no reviews, stars, or paid placement. This gives agent-facing guarantees about data semantics and trustworthiness.

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 description is dense and front-loaded with the core purpose, followed by distinct behavioral facts. Each sentence earns its place—the sealed explanation, real counts, empty query, and fallback to publish_app are all valuable. It is slightly long but not wasteful.

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?

Given no output schema and no annotations, the description provides an unusually rich picture: exact result fields, the meaning of 'sealed', the nature of counts, and the fallback action if no results match. This is more than sufficient for an agent to select and invoke the tool correctly.

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?

The input schema already provides 100% coverage with descriptions for both q and sort. The description only adds the empty-query convention ('An empty query lists the whole shelf'), which is a small addition. Baseline 3 is appropriate when the schema does the heavy lifting.

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 begins with a specific verb and resource: 'Search Postapp's library of instantly published single-file web apps.' It enumerates exact return fields (name, one-line description, live URL, allowed hosts) and clearly differentiates from siblings publish_app and remove_app by focusing on search, not publishing or removal.

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 description explicitly states when to use this tool vs. the alternative: 'If nothing matches, the gap can be filled: publish_app takes one HTML file.' It also clarifies that an empty query lists the whole shelf, giving clear contextual use cases. No exclusions are needed for a search tool.

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