tv_logs

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

Annotations already cover safety (readOnly, non-destructive, closed-world), so the description's main contribution is the privacy warning that output may contain private app data — genuinely useful context beyond structured fields. It omits other useful behavior: whether output is a snapshot or a tail, and what happens if the PID is absent.

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, no filler, and the scoping constraint is front-loaded before the privacy caveat. Nothing is redundant with the tool name.

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 output schema means return values need no explanation, and the privacy note covers the main risk. Still, for a tool whose only precondition is a live process, the description leaves out behavior on a missing PID, output ordering/recency, and any account of the `lines` cap.

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 description must carry parameter meaning. It clarifies that `package` refers to a package with a running process, but the `lines` parameter (default 50, max 200) is never mentioned, and neither is the expected package identifier format.

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 ("Read recent logs") plus a scope constraint ("only for one running PID of a selected package"). It is clearly distinguishable from the sibling tv_* control tools, though it never frames itself as the diagnostic/log-inspection companion to 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 "one running PID" implicitly tells the agent a prerequisite: the package must currently be running, and only its process's logs come back. There is no explicit when-to-use vs alternatives (e.g. tv_status or tv_packages for non-log diagnostics) and no guidance on what to do when no process is running.

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