read_adb_logcat

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

The description adds real behavioral detail (bounded snapshot, newest-lines-wins truncation, no clear/stream), but it closes with an explicit "Read-only." claim while annotations declare readOnlyHint=false. That direct conflict undermines trust in the stated safety profile, even though the remaining behavior is well disclosed.

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?

Three short sentences, front-loaded with the operation and scope, then exclusions, then the safety claim. No filler and nothing buried.

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 should say what comes back; it implies raw log lines but never states the return shape (text vs structured entries, line format). Everything else needed to call it — buffer choice, pid filter, count cap behavior, non-destructive scope — is covered.

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 coverage is 100%, so every parameter (pid, count, buffer, serial, analysis_project_id) is already documented in the schema. The description adds only framing — "one buffer" and "optionally restricted to a process id" — plus a truncation note that largely restates the count parameter's schema text, so the baseline 3 applies.

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?

States a specific verb and resource (bounded dump of the device log via `logcat -d -t`), including scope: one buffer, optionally one pid. This clearly distinguishes it from siblings like collect_adb_bugreport or list_adb_processes.

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 streaming, no clearing" plus "the newest lines are kept when the count cap trims" tells the agent what this tool is not for and how it behaves at the cap. It never names an alternative tool to use when streaming or clearing is actually needed, so it stops 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.