shield_logcat

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

Annotations already declare the safe read-only profile, and the description adds two pieces of genuinely useful context: output is 'bounded' (limited tail) and 'Redaction is best effort', warning the agent that sensitive data may not be fully masked. It stops short of stating the actual bound or whether truncation is signalled.

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 short sentences with no filler; the core purpose is front-loaded and the caveat follows. Nothing could be removed without losing information.

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?

An output schema exists, so return values need no explanation, and the annotation covers the safety profile. The remaining gap is the undocumented 'lines' parameter and any connection precondition, which a one-param read tool should still address.

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 single 'lines' parameter (default 150) is documented only by its title and default. The description's 'bounded log tail' implies a line-count limit but never ties it to the parameter or explains the tail direction or maximum allowed value.

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?

Specific verb (Read) plus resource (Android log tail) and scope qualifier (bounded), with a stated use case (native crashes). It is distinguishable from the kodi_* log/read siblings by naming the Android platform, though it does not explicitly contrast with them.

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 phrase 'for native crashes' implies a narrow use case, but there is no explicit when-to-use guidance, no mention of alternatives (e.g. shield_status for general diagnostics), and no prerequisites such as needing an active connection.

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