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

Annotations already declare destructiveHint=true, readOnlyHint=false, openWorldHint=true, and idempotentHint=false, so the agent knows this is a non-idempotent, state-changing operation. The description adds useful state preconditions for both the thing and the draft, but never explains what 'locking' actually does to the thing, whether it is reversible, or what the result is.

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 action is front-loaded and the sentences are reasonably tight, but the opaque code '1F3EA' and the tacked-on 'Lost? Call front_door' add noise rather than clarity. It is neither wasted nor well-structured.

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 destructive two-parameter mutation with no output schema, the description gives precondition context but omits what happens on success, reversibility, and any explanation of the parameters. An agent can infer prerequisites but not the full effect of the call.

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 description coverage is 0% and the description never mentions thing_id or market_draft_id, their formats, or their expected values. It refers obliquely to 'one thing' and 'the matching draft' but leaves both integer parameters effectively undocumented.

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 and resource ('Lock one thing you own for a pending ... world-aisle draft'), which tells the agent this is a locking/mutation action. However, it clashes with the name 'list_world' and title 'List a world thing', which imply a read, and the phrase '1F3EA world-aisle draft' is opaque jargon. No sibling tool is named as a distinction point.

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 lists solid preconditions for use (thing must be owned, not withdrawn, unlocked; draft must be pending, unexpired, unlisted), which is genuine when-to-use context. But there is no explicit when-not guidance and no named alternative apart from the vague 'Lost? Call front_door' fallback.

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