Read the worker's stage conclusion

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

No annotations provided, so description carries full burden. Discloses read-only nature, repeatable calls, and internal content. Highlights critical failure mode (confusing drift with conclusion). Does not cover permissions or all failure modes, but sufficient.

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 purpose, then details. Slightly long but every sentence adds value. Could be more concise but still effective.

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, but description explains return contents (content tail, step tail, progress files, driftHint, runlog). Covers read-only and repeatable use. Lacks explicit return format but complete enough for tool usage.

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 75% (3 of 4 params described). Description adds context for stepTail (max steps) and contentChars (text limit), but does not introduce new semantics beyond schema. driftHint/runlog advice is behavioral, not parameter-specific.

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?

Description clearly states it reads the worker's stage conclusion, listing included elements (content tail, step tail, progress.md/ledger.md, driftHint, runlogTail). Distinguishes from sibling tools like agent_send (sends messages) and agent_runlog (reads runlogs).

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?

Explicitly says when to use (read conclusion for director judgment) and warns about misinterpreting driftHint/runlog. States it is read-only and callable repeatedly, implying no side effects. Lacks explicit alternatives but context suffices.

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