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

Annotations already cover the safety profile (readOnly/idempotent/non-destructive), and the description adds substantial context beyond them: no credential needed, only the decision is returned and never the unreviewed content, the id is unguessable (`lst_…`), the listing page stays owner-only until public, and responses are cached for 60 s per point of presence. This is exactly the extra behavioral context annotations cannot carry.

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?

Purpose and states are front-loaded, and most sentences carry real information (caching, credential-free access, visibility rules). It loses a point for redundancy: 'only the decision comes back' is asserted twice in near-identical form, and 'per point of presence' is jargon that costs reading time without adding clarity.

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 single-parameter, read-only polling tool with no output schema, the description is complete: it explains what is returned (the decision, not content), the state vocabulary, the lifecycle (born pending, auto-review, human review for uncertain cases), and how often to poll. Nothing needed to call it correctly is missing.

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% and there is only one parameter, so the schema already documents `id`. The description still adds meaning: the id is unguessable and prefixed `lst_…`, and it comes from the `POST /api/listings` response, reinforcing provenance beyond the schema's own wording.

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 resource and action: the moderation state of a listing, with the enumerated states (pending/live/low/hidden/blocked) and the trigger point ('poll it after create_listing'). It is clear what the tool returns. It does not explicitly distinguish itself from siblings like get_listing or listing_history, which also surface listing data, so sibling differentiation is left implicit.

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 a concrete when-to-use: poll after `POST /api/listings`, whose response carries this URL as `status_api`. It also gives cadence guidance ('poll every few minutes, not every second'). No explicit when-not-to-use or named alternative (e.g., why not get_listing), which keeps it below 5.

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