read_runtime_logs

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

Annotations only declare readOnlyHint and openWorldHint=false, so the description carries real additional burden and delivers: default level=warn, reverse-chronological ordering, pagination meta fields, exception serialization format, and the important 'empty result is success, not an error' note. It stops short of describing rate limits or log-source coverage boundaries, so not a full 5.

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?

Front-loaded with the core purpose and signal value, then ordering/pagination, then defaults, then the exclusion. Dense but every sentence contributes; slightly long for a read tool.

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?

No output schema exists, yet the description explains the return shape (paginated entries, meta total/count/hasMore/nextCursor, exception serialization) plus the launch_start precondition. An agent has everything needed to call and interpret it correctly.

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 genuine meaning: it clarifies that level is a minimum-severity filter (not an exact match), states the default, and explains that keyword does case-insensitive text filtering. This exceeds what the schema alone conveys.

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+resource ('Read console output ... from the RUNNING Launch instance') and enumerates the exact content types (log/info/warn/error, uncaught exceptions, unhandled rejections). It explicitly distinguishes itself from the sibling read_editor_logs by scoping to the launched app only.

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 prerequisites ('Requires launch_start first') and an explicit 'When NOT to use' clause routing the agent to editor logs instead. The default severity and the level='all' widening behavior are also spelled out, leaving nothing to inference.

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