Publish Task Report

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

Annotations already declare idempotentHint=true, readOnlyHint=false, destructiveHint=false. The description adds value by confirming the idempotent write nature, stating it cannot alter state, and indicating it is 'bounded' (max lengths across inputs). These go beyond what annotations flag, though some granular behavior (e.g., total bounded size limits across all fields, return value) is left to the output schema.

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?

Two tight sentences in the description, both earning their place—first states the operation+scope, second states the limitation boundary. Zero filler, front-loaded with the primary action. The extensive parameter documentation lives in the schema where it belongs rather than bloating the description.

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?

Despite 11 parameters, the tool is well-covered: full schema descriptions, an output schema documenting return values, idempotence and boundedness conveyed in the description, and clear state-boundary disclosure. The complexity is high but every dimension (purpose, scope, constraints, idempotency, workspace binding via workspace_id/workspace_generation/conversation_id) is covered between description and structured fields.

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 schema documents all 11 parameters with descriptions. The description adds semantic context by framing it as 'one bounded... update' in a single procedural write operation, and top-level text conveys the overall purpose of the primary inputs (summary, idempotency_key). The enum-driven severity and event_kind defaults are well-explained in the schema.

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 opens with a specific verb+resource ('Append... to an existing task in the active workspace') and clearly delimits the scope ('idempotent explanatory report write only'), listing what it cannot change (task, validation, Git, completion state). It distinguishes itself from write/edit/bash tasks and task_complete siblings by emphasizing it is a bounded explanatory report append.

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 states when to use it ('ChatGPT-authored public progress update, summary, finding, or warning') and explicitly what it cannot do, which functions as exclusion guidance. It doesn't name the sibling alternatives (e.g., run_task_status, task_complete) explicitly, but the boundary against state-changing tools is clear enough to navigate choices.

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