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

Annotations already cover safety (readOnly, idempotent, non-destructive), and the description still adds substantial behavior: a throwing TypeScript component is switched off rather than breaking preview and the reason lands on channel scene, decoder failures land on preview-video, failed tool calls land on chat with input, and tracking logs downloads/worker boot/errors. It also discloses defaults (120s, warn+error, newest 40) and how afterSeq pages. This is well beyond what the annotations provide.

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?

Dense but front-loaded: the channel taxonomy comes first, then the failure modes, then the call conditions, then the defaults and knobs. The channel inventory is long, yet each entry carries real diagnostic routing information rather than filler, so nearly every sentence earns its place.

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?

For a read-only tool with no output schema, the description conveys the log line formats ([component] lines, 'tool <name> failed: <reason>'), the defaults, and the paging mechanism, which is enough to call and interpret it. It does not describe the overall return structure or ordering beyond 'newest 40 lines', a minor remaining gap.

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 the baseline is 3, but the description adds usable intent on top: channels narrows, levels widens to info, sinceSeconds extends the window, and afterSeq pages past a line already seen. That maps each parameter to a practical purpose rather than restating its type.

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 the editor's recent log') and then enumerates exactly which producers feed it (scene, preview, preview-video, web, chat, tracking). No sibling tool reads logs, so the scope is unambiguous and the agent can tell it apart from read_render, read_component, or read_analysis_range.

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?

Gives a concrete trigger list: component does not appear, preview reports a failure, a tool call fails, or after a write to confirm nothing complained. That is strong when-to-use context, but there are no when-not conditions or named alternatives to compare against (none exist among the siblings).

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