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

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=true, so the description's strongest contribution is the side-effect disclosure: "The post it lives in gets a revision the writer can undo." That tells the agent changes are reversible and create a revision, which is real value beyond the annotations. It does not explain what the opaque "pixelglass://blocks/contract" reference means for the caller.

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?

Only three short sentences, but they are fragmented and the final sentence ("The contract in pixelglass://blocks/contract still holds") is a cryptic pointer that consumes space without explaining a constraint to the agent. Side-effect information would be better front-loaded ahead of the dangling contract reference.

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 four-parameter mutation tool with no output schema, the description covers the essential reversibility and revision behavior, which is the right instinct. It leaves gaps around what the response contains and what the referenced block contract enforces, so an agent still has to guess at the validation rules it must satisfy.

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 75%, so the schema already documents site, html, and height including the "leave out to keep it" partial-update semantics. The description adds provenance only for uuid via the get_post pointer, since uuid has no schema description. That is a genuine but small increment over structured data.

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 conveys that it sets a document or height on a block identified by uuid, which is more specific than the title alone, but it is written as a verbless fragment ("A new document or height for an artifact block") and uses unexplained jargon ("artifact block"). It never states plainly that this replaces existing block content, nor does it distinguish itself from adjacent siblings such as create_block, delete_block, or edit_post.

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?

Usage is only implied: you use it to change a block's html or height on a specific site. The one explicit routing hint is useful — "by its uuid (get_post lists them)" tells the agent where to obtain the identifier. There is no statement of when not to use it or which sibling to pick for adjacent tasks.

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