Task Status

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds value by disclosing the live projection nature (from multiple authoritative sources) and uses the word 'read-only' redundantly but consistently with annotations. No contradiction; it provides reasonable context beyond the structured fields.

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, compact sentence that efficiently conveys the purpose. It uses precise terminology (unified, projected live, authoritative, Goal/Durable Job/Handoff). Slightly jargon-heavy for a non-expert, but economical with strong front-loading of the verb and read-only nature.

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 status retrieval tool with an output schema present and good annotations, this is largely complete. The description conveys the unified-source behavior and the live/authoritative nature. The main gap is not explaining what the returned status structure looks like beyond the output schema, but since an output schema exists, the description needn't carry that burden. The term 'Handoff' and 'Goal' are domain-specific but reasonable for this context.

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 67%: task_id and workspace_id are documented in the schema, but conversation_id is not described in the description. The description adds the 'unified' and 'live' semantics that clarify what task_id resolves to, but it doesn't explain parameter relationships or how the three parameters interact. The description works with—but doesn't substantially extend—the schema's parameter descriptions.

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 has a specific verb+resource ('Read one unified, read-only task status') and clearly states what it returns - a status projected from Goal, Durable Job, or Handoff state. It's distinct in that it provides a unified view across sources, though sibling tools like 'current_task' and 'run_task_status' overlap in purpose, and the description doesn't explicitly differentiate them.

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 implies this is for reading a live, authoritative status snapshot, which clarifies when to use it versus other state-tracking tools. However, it doesn't explicitly state when NOT to use it or point to alternatives like 'current_task' or 'run_task_status', and siblings are numerous with overlapping read/status functions leaving the selection reasoning implicit.

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