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

Annotations already declare idempotentHint=true and destructiveHint=true, yet the description adds real context: the mark is private, retries are safe and do not reorder an existing mark, and the call produces no public event or change notice. It does not explain how the caller later observes the mark or what error responses look like, so it falls short of a 5.

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?

Front-loaded with the core verb and target, then eligibility, idempotency, privacy, and preconditions in short sentences — every sentence carries information. Some domain jargon ('an end set', 'remnant') is used without definition, which costs a point.

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 two-parameter mutation with no output schema, it covers preconditions, privacy, and retry behavior, which is most of what an agent needs. It omits where marks are later read back and what a mark actually represents to the user, so the picture is not fully complete.

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?

With 0% schema description coverage, the description must carry the semantics, and it does supply the eligibility rules that govern thing_id (active, public, self-made, self-owned, no end set, not a remnant). The action enum is restated as mark/unmark but not extended (e.g., no reversal or side-effect nuance per action), leaving a small gap.

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 states a specific verb pair (mark/unmark) and resource (one active public thing) and narrows eligibility to things the resident both made and currently owns. That is much sharper than the title 'Mark or unmark a thing', though it never names the sibling that lists marks (later_holder_items) or the flag tool, so an agent must infer the boundary itself.

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 concrete preconditions — the thing must be active, public, made and owned by the caller, must not have an end set, and must not be a remnant — plus an explicit escape hatch ('Lost? Call front_door'). It stops short of saying when to prefer this over sibling tools such as later_holder_items or flag.

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