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

Annotations already declare a safe read (readOnly, idempotent, non-destructive, closed-world), and the description adds real value beyond them: it discloses the implicit filter (only not-done items) and the payload shape (description, subtasks, new notes, thread). It stops short of stating volume, ordering, or what an empty result means.

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 returned-content list is front-loaded, which is good, but the parenthetical '(the last notes between you and the user, yours too)' is tangled and costs more parsing than it saves. The middle sentence also runs the payload inventory and the trigger conditions together rather than separating them.

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?

With no output schema and no parameters, the description carries the burden of telling the agent what comes back, and it does so at a reasonable level of detail. What is missing is of secondary importance: ordering, expected volume, and whether the agent's own notes are distinguishable from the user's in the returned thread.

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 tool takes zero parameters and the schema is fully closed, so there is nothing for the description to disambiguate. Baseline 4 applies; the description does not mislead about inputs.

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 names a specific resource and scope: undone tasks handed to an AI agent in Aimgod, returned with their descriptions, subtasks, user notes, and thread. That distinguishes it in substance from get_tasks/get_today, though it never names those siblings directly, so the differentiation must be inferred from 'handed to an AI agent'.

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?

It gives two concrete triggers: the user asks to take their Aimgod work, or a scheduled Aimgod worker run starts. It also adds an important usage constraint — 'Do the work with your own tools; Aimgod only shows its state' — but offers no explicit exclusion pointing to get_tasks for non-agent work.

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