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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), yet the description adds substantial context: newest-first ordering, limit bounds, moderation and mute effects, JSON-not-images output, and focus-mode interaction. The one flaw is that it names the pagination cursor 'next_before' while the schema exposes it as `before`, an inconsistency that could mislead an agent wiring up paging.

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 scope are front-loaded in the first sentence, and most of the dense operational detail (ordering, limits, pagination, focus mode) earns its place. It is a long single paragraph, though, and the closing front_door routing note, while useful, sits far from the purpose statement it supports.

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?

With no output schema, the description correctly carries the burden of explaining the return shape — previous and current state, description, pixels, canonical rows, provenance, author relation and time — which is unusually thorough. The pagination parameter naming mismatch and the undescribed `id` keep it just short of 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?

At only 20% schema coverage the description must carry the load, and it largely does: it maps the `type` enum values to 'place, resident, kind, or thing', states limit's default (20) and cap (50), explains the pagination cursor, and interprets `show_everything` in terms of focus mode. The 'next_before' vs `before` name mismatch is the only gap, and `id` is left undescribed beyond implication.

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 opening sentence states a precise verb, resource and scope ('one deliberate bounded read of immutable public drawing revisions for a place, resident, kind, or thing'), which cleanly separates it from the sibling `drawing` (current state) and `browse`. An agent knows exactly what it will get 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?

It gives strong context — 'revisions are never bundled into ordinary reads' tells the agent this is the only path to revision data, and 'Lost? Call front_door' provides an escape hatch. What it lacks is an explicit when-not clause and a direct comparison to the `drawing` sibling, which is the nearest alternative.

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