get_run_logs

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

With no annotations to carry safety or side-effect info, the description does a solid job: it details return event types, explains the level_filter ordering and special inclusion of failure events, and describes pagination via cursor. It could be more explicit that this is a read-only operation and doesn't mention rate limits, but these are minor omissions given the thoroughness.

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 well-structured with a lead summary, event details, a parameter list, and a usage note. It is front-loaded with the core purpose, and every sentence adds value—no filler or repetition. The organization makes it easy to scan.

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 use case well, including return event structure, filtering behavior, and pagination. It points to a sibling for alternative usage. However, it does not mention the 'env' parameter, possible error conditions, or rate limits. Given the tool's complexity and the absence of annotations, these omissions leave some ambiguity, though not enough to prevent correct use.

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 description explains run_id, level_filter (with detailed semantics), cursor (pagination), and limit (default), but completely omits the 'env' parameter that appears in the schema. Since schema description coverage is 0%, this gap means the agent must guess the purpose of 'env'. The documented parameters are explained well, but the missing one prevents a higher score.

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 'gets structured log events for a run' with optional filtering and pagination. It distinguishes itself from sibling tools by explicitly referencing get_run_failure_summary as the alternative for quick failure diagnosis, making its purpose unambiguous.

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 description includes a dedicated 'When to use' section that tells the agent exactly when to prefer this tool ('full event stream or filter by level') versus the sibling get_run_failure_summary for consolidated failure info. This is explicit and actionable.

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