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

Annotations are minimal (readOnly=false, destructive=false, etc.), so the description carries the burden of behavioral disclosure. It discloses the side effects: 'The org gets pinged; the thread shows in both the worker portal and Simple Mode.' It also explains that the created list is linked into the parent's thread and aimed at the sender. It doesn't mention reversibility or whether the creation is idempotent, but annotations already signal non-idempotent and the description covers the essential side-effect context.

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 paragraph with the core purpose front-loaded and valuable examples included. Every sentence contributes: purpose, mechanics, side effects, and follow-up guidance. It is slightly dense with examples and inline tool references, but avoids fluff and remains scannable.

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?

Given the tool's complexity (creating a list with typed tasks, response_config, threading), the description covers the main conceptual pieces: what the tool does, what happens in the UI, how recipients answer (typed tasks), and how to read the answers. No output schema exists, so return format is not described, but the description points to tascan_list_projects/tascan_get_report for reading answers. Minor gaps: no mention of author_name defaults or whether parent_list_id must be a list rather than a project, but overall sufficient.

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 description coverage is 100%, so the schema fully documents parameter meanings. The description adds extra semantic value by explaining response_type usage ('date' for scheduling windows, 'text' for info requests, 'choice' needs response_config.options) and providing example titles. It doesn't describe author_name behavior, but the schema already states 'shown in the thread.' The description enhances rather than repeats the structured data.

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's purpose: 'Reply to a task list WITH a task list — the two-way tasking primitive.' It specifies the verb (reply/creates), the resource (a new list linked into the parent's thread), and distinguishes it from siblings by emphasizing it creates a new list aimed back at the sender, not merely adding tasks to an existing list. The examples and direction ('aimed back at whoever sent the original') make the unique role clear.

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 gives clear usage context: it's for replying to a task list with a task list and explains the resulting behavior (org gets pinged, thread shows in both worker portal and Simple Mode). It implicitly contrasts this with alternative follow-up methods by mentioning 'Use tascan_get_thread-style follow-up via tascan_list_projects/tascan_get_report to read answers,' which guides the agent to use separate tools for reading responses. It does not explicitly name sibling tools for creating normal lists or adding tasks, so exclusion guidance is partial.

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