manage_logs

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

With no annotations, the description carries the full burden of disclosing behavior. It mentions the log source and the 'clear' action, but does not warn that 'clear' is destructive or explain any side effects of the read actions. Permissions, rate limits, or data retention are also not addressed.

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?

The description is a single dense sentence that front-loads the main purpose and then lists actions in a compact structure. It avoids wasted words, though the packed list could be slightly more readable with line breaks.

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 description covers the main actions and filters, but omits important context such as the default limit, return format, and the irreversibility of 'clear'. Given no output schema and no annotations, this leaves gaps for an agent to fully understand consequences and expected responses.

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?

The schema already describes most parameters, but the description adds valuable semantics: it clarifies 'since' as a unix-seconds cursor, maps 'errors' to Error-level only, and labels levelFilter values. This goes beyond the raw schema and helps the agent use filters correctly.

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 clearly states the tool reads the Roblox Studio output log and enumerates specific actions (get, errors, clear), making its purpose unambiguous. This distinguishes it from sibling tools like query_instances or execute_luau, which focus on other concerns.

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?

It provides clear context on log sources (plugin via LogService, play-mode from play agent) and describes each action's filter parameters. However, it does not explicitly state when to prefer this over alternatives or when not to use it, but the context is sufficient for typical use cases.

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