get_app_knowledge

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds valuable behavioral context: that ui_shape may be returned even when known=false, and that the data was learned passively from earlier reads. This explains what to expect from the tool beyond the structured annotations.

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 a compact but information-dense paragraph. Each sentence serves a purpose: purpose, usage timing, ui_shape caveat, and parameter guidance. It is not overly terse, and the structure flows logically from main purpose to additional details. Slightly verbose but every sentence 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 carries the burden of explaining return values. It covers the main data types (recipes, common_failures, ui_shape) and the known=false case. It does not detail the exact JSON structure, but for an AI agent this level of context is sufficient to understand what the tool returns and how to use it.

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 the 'name' parameter with an example, but the description adds 'Pass the process name as shown in task manager,' which clarifies the exact format expected. This is meaningful addition beyond the schema, and schema coverage is 100%, so the baseline is already high.

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 queries learned knowledge about an app, specifying the content: successful action recipes and common failures. It distinguishes itself from sibling tools like read_window or get_ui_tree by focusing on learned knowledge rather than direct UI reads. The verb 'Query' and resource 'what AIPM learned locally about an app' are specific and unambiguous.

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 says 'Call BEFORE acting in an app,' which is clear when-to-use guidance. It also tells the agent not to retry common_failures, which is actionable context. However, it does not explicitly name alternative tools or state when not to use this tool, so it falls short of a 5.

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