library

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

With no annotations, the description carries the full burden of behavioral disclosure and excels. It details the security model (browser blocks outbound requests, external hosts allowed), privacy (device permissions off unless used), live deployment, PWA auto-adding, source availability, ranking formula, and the 90-day removal policy. This is exceptionally transparent about side effects and limitations.

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 long but information-dense; every sentence conveys a meaningful behavior or constraint. It is front-loaded with the core purpose and then details security and persistence. While it could be seen as verbose, the complexity of the tool justifies the length and there is no wasted text.

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 9 parameters and no output schema, the description covers nearly all aspects: what it returns, security behavior, derived metadata, override semantics, and removal policy. The only gap is that it never explicitly states that one of html or url is required (though the prefix 'Instead of html' implies it). Overall, it is very complete for the tool's complexity.

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 descriptions cover 100% of parameters, so the baseline is 3. The description adds value by explaining that metadata (name, icon, category, tags) is derived from content and passed only to override, clarifying the optional nature and purpose of these parameters. This enhances understanding beyond the schema.

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 opens with a specific verb and resource: 'Publish one self-contained HTML document to Postapp' and clearly states the destination. It differentiates from sibling tools by mentioning that published apps are 'immediately findable via search_apps' and the existence of remove_app for removal. The purpose is unmistakable.

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 clearly implies when to use this tool: to publish an HTML app to Postapp. It contrasts with search_apps (finding apps) and remove_app (removing apps) indirectly. However, it does not explicitly state conditions for not using it, such as needing server-side code or inappropriate content, but overall the context is clear.

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

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

With no annotations, the description carries the full burden and does so thoroughly: it reveals the app leaves the shelf, the address serves a tombstone, the reason is published verbatim with a date in a permanent public ledger, and the removal record is permanent. This is exemplary transparency about irreversible, public consequences.

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 four sentences, each earning its place: main action, effect on the app, ledger policy, and permanence. It is front-loaded with the primary verb and stays free of filler.

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 simple 2-parameter tool with no output schema, the description fully covers the action, its public and permanent consequences, and the necessary context. It doesn't explain return values or errors, which isn't essential here.

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 schema already covers both parameters (slug and reason) at 100%, and the description adds significant meaning to the 'reason' parameter by noting it is required and published verbatim in the permanent ledger. It adds nothing new for 'slug,' but the overall enrichment justifies a score above baseline.

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 clearly states the tool's function: 'Take down an app published with your key.' This is a specific verb+resource combination that distinguishes it from siblings like publish_app and search_apps, and it clarifies whose apps can be removed.

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 implies when to use the tool (for an app you published) and hints at a prerequisite ('with your key'), but it doesn't explicitly name alternatives or when not to use it. The context is clear enough, though exclusions are absent.

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

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.