aiworkhub_manager_loop_discard

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the danger profile is conveyed structurally. The description reinforces that a conversation is deleted but adds nothing beyond the annotations: no statement of reversibility, no confirmation that the deletion is permanent, and no note about what happens to associated messages or events.

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?

A single short sentence with a leading category tag ('MANAGER WRITE') that front-loads the mutation intent. No filler, though the terseness is partly achieved by omitting useful detail.

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?

An output schema exists and annotations cover the safety profile, so return values and risk are handled elsewhere. Still, for a destructive single-object deletion the description is thin: it doesn't clarify what a 'saved manager conversation' is or what session_id refers to, leaving gaps an agent might need to resolve.

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 0% and the description never mentions the single required parameter session_id, so it fails to compensate for the gap. With only one parameter the burden is small, keeping this at a minimum-viable 3 rather than lower.

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?

States a specific verb ('delete') and resource ('one saved manager conversation'), making the operation clear. However, it does not distinguish 'discard' from related siblings like loop_close, loop_stop, or loop_rename, leaving a small ambiguity about which deletion-ish tool to pick.

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 'MANAGER WRITE' prefix hints at write context, but there is no explicit when-to-use guidance nor any statement about when NOT to use this versus loop_close, loop_stop, or loop_archive-style siblings. The agent must infer selection from the name alone.

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