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

Annotations already declare non-readonly, idempotent, non-destructive, closed-world behavior, so the description's added value is the domain rule that self-checked items can be skipped but never marked done — a constraint absent from structured data. The 'brings it back' phrasing also discloses that the change is reversible, reinforced by idempotentHint. It says nothing about what happens on an invalid transition for a non-skippable item.

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?

Three short sentences, front-loaded with the operation and its states before the usage rules. The dashboard analogy ('like the checkbox and Skip') is compact and load-bearing for the mental model; no filler.

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 2-parameter mutation with no output schema, the description covers state meanings, the user-intent trigger, and a hard eligibility rule. Missing only error/edge behavior — e.g., what is returned or happens when someone marks done an item the system checks itself.

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 baseline is 3, but the description adds intent mapping beyond the enum list: 'done' corresponds to the user asserting completion, and 'brings it back' glosses 'open' as a reopen action rather than leaving the raw enum value to interpretation. action_id semantics come entirely from the schema and are not duplicated.

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+resource pair — 'Marks an Action Center item done, skips it, or brings it back' — and enumerates the exact state transitions. An agent can separate this from list_actions/get_action (read) and from approve_changes/dismiss_change (change review) without opening the schema.

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?

Gives an explicit trigger for the 'done' state ('Use done when the user says they've done it') and an eligibility restriction ('Items LinkGPT checks itself can be skipped but not marked done'). It stops short of routing to alternatives for inspecting an item first, so no exclusion guidance against siblings.

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