read_logs

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It discloses the source (stdout/stderr) and scope (last N lines), but doesn't disclose what happens if the app isn't running, whether logs are buffered/truncated, or return format. For a read-only tool the risk is low, but the description doesn't add much beyond the raw statement.

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?

One sentence, perfectly sized for the tool's simplicity. Every word earns its place — verb, resource, and scope in a single line. No fluff or repetition.

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?

The tool is simple (1 optional param, no output schema). The description covers the basic function adequately. However, it doesn't mention what the output looks like (plain text lines? structured?), whether the default 50-line behavior is significant, or any relationship to timing of log capture. For such a simple read tool, this is adequate-but-minimal.

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% (the single 'lines' param has a description and default). The tool description adds 'stdout/stderr' context but doesn't add meaning to the parameter beyond what the schema already specifies. Baseline 3 is appropriate since the schema adequately documents the parameter.

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 states 'Reads the last N lines from the app's stdout/stderr' — a specific verb (reads) plus resource (app logs) and clear scope (last N lines, stdout/stderr). It distinguishes from siblings like start_app/stop_app which are lifecycle actions, though it doesn't explicitly differentiate from other diagnostic tools like get_widget_tree.

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?

No guidance on when to use this tool versus alternatives, nor any exclusions. It doesn't clarify when log reading is appropriate (e.g., after failures, for debugging) versus other diagnostic tools like assert or get_text. There's no mention of prerequisites like app running state.

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