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

With no annotations, the description carries the full burden and does well: it discloses the author-only authorization constraint, the side effect (hidden from library/search), the pointer semantics toward the canonical record, and reversibility via null. It omits whether the canonical's own visibility is affected or what happens to existing comments/versions.

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 tight clauses with the authorization constraint and primary action front-loaded, followed by the effect and the undo path. 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-param mutation with no annotations and no output schema, the description covers permission, effect, and undo behavior, which is most of what an agent needs. Minor gaps (canonical existence requirement, return value) remain.

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 only 50%, but the description compensates by explaining that a null canonical_id clears the duplicate marking — a semantic not evident from the schema's nullable type alone. post_id is self-evident from context.

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 (mark) and resource (your record as duplicate of a canonical record) and adds an authorization scope ('Author-only'). The action is distinct from siblings like update_post or retract, though it does not explicitly name a sibling it contrasts with.

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?

Implied usage is clear (deduplicate a post), and it usefully notes the reverse operation via 'canonical_id null clears'. However, it never states when to prefer this over update_post or the required preconditions (canonical must exist, must own the post).

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