get_app_screenReturn a non-secret semantic description of an important Aperture screen, its purpose, entry points, sensitivity, and safe agent actions. This does not inspect a user device or wallet.
| Name | Required | Description | Default |
|---|---|---|---|
| screen_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish read-only, idempotent, and non-destructive behavior. The description adds meaningful context beyond those annotations by stating the result is 'non-secret' and that the tool 'does not inspect a user device or wallet,' which clarifies privacy and safety expectations for an agent.
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 two tightly written sentences with no filler. The primary return value and scope are front-loaded, and the safety clarification is placed at the end without adding unnecessary length.
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 single-parameter read-only tool with no output schema, the description covers what is returned and what the tool does not do. It is slightly incomplete only in that it does not tell the agent how to obtain or format a valid screen_id, which is the sole input.
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 0%, so the description must compensate for the undocumented screen_id parameter. It does not describe how screen_id should be sourced, what it represents beyond 'screen,' or how it relates to sibling tools such as list_app_entry_points. The regex pattern in the schema provides format but not semantic meaning.
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 uses the specific verb 'Return' and identifies the resource as 'a non-secret semantic description of an important Aperture screen.' It also enumerates the content of the result (purpose, entry points, sensitivity, safe agent actions), which makes the tool's function unambiguous and distinct from sibling get_* and list_* tools.
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 intended use is implied by the description: call this when you need a semantic screen description rather than raw data. However, it does not explicitly state when to prefer this over siblings like list_app_entry_points or get_feature, and it names no alternatives or exclusion conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools target distinct resource types (product, security, features, articles, networks, release, screens, entry points), with get_/list_ pairs clearly separating single-item retrieval from collection listing. The only mild ambiguity is between get_app_screen and list_app_entry_points, since both describe UI navigation surfaces, though their descriptions keep screen semantics vs entry-point catalogs separate.
The dominant get_<singular> and list_<plural> pattern is clear and predictable for 10 of 12 tools. 'search' and 'fetch' break the noun-oriented pattern and are less descriptive of their distinct roles, but they are common enough verbs that the overall set remains readable.
With 12 tools, the server is well-scoped for a wallet knowledge base: each get tool corresponds to a distinct knowledge category and list tools cover discoverability. No tool feels redundant, and the count is squarely in the appropriate range.
The surface covers the major knowledge domains an agent needs: product identity, security model, features, articles, supported networks, release info, app screens, and entry points, plus search/fetch for open-ended lookup. Minor asymmetries exist (e.g., get_app_screen has no listing counterpart, and list_app_entry_points has no single-item get), but these are workable through search.