app_list

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

Annotations already provide readOnlyHint=true and openWorldHint=true, so the safety profile is well covered. The description adds the semantic context that filtering options exist (name partial match, system vs third-party), which is genuinely useful beyond annotations. However, it doesn't disclose output format, potential length limits, or pagination behavior, though with an output schema present and readOnlyHint already set, the description's contribution to transparency is adequate.

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?

Two sentences with zero redundancy. The opening states the core function, followed by optional filters and a cross-tool use case. Every word earns its place—no filler, no repetition of the schema, and it's front-loaded with the primary action.

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 readOnlyHint and openWorldHint annotations covering the safety profile, 100% parameter schema coverage, and an output schema present, the description's role is minimal. Adding the cross-reference to app_start (the primary downstream consumer) is a smart, complete touch. For a simple list-style read tool, this is fully adequate.

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 100%, so all three parameters (filter, serial, system) are documented in the schema. The description's mention of 'filter by name or restrict to system/third-party apps' roughly mirrors what the schema already says. The description adds marginal value by framing these as use cases (finding apps by name, restricting to system/third-party), but doesn't go meaningfully 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 clearly states 'List installed packages on the device' with a specific verb (list) and resource (packages). It distinguishes itself by offering optional filtering by name or system/third-party classification, and explicitly ties its use to finding package names for app_start, separating it from sibling tools like app_current, app_start, and device_info.

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 states the purpose context—'Use to find package names for app_start'—which implies when to use it. However, it doesn't explicitly state when NOT to use it or name alternative tools like device_info or app_current for different package-related queries. The system/third-party filter guidance is present but implicit in the filter semantics.

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