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

Goes well beyond the annotations: omitted blocks are deleted with no warning, concurrency is guarded by version, image URLs are downloaded and stored (with a failing-write behavior naming the offending block), and nothing needs uploading. This surfaces destructive and side-effect detail the destructiveHint/idempotentHint flags cannot convey.

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?

Front-loads the replace semantics, then layers warnings, workflow, image behavior, and return values in a tight sequence. Four dense sentences with no filler, though the final return-value sentence is somewhat redundant given an output schema exists.

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, nested-object, whole-document write, it covers the data-loss risk, concurrency protection, side effects, prerequisite read, and even return shape. An output schema exists, so the brief mention of url/pages is bonus rather than necessity.

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%, so the baseline is 3, but the description adds real meaning: version's role as a stale-write guard, blocks must be the complete list, and the pointers into the keepp://capabilities resource and keepp.link/<handle> handle format. It stops short of documenting the theme object's contents.

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 and resource with scope: 'Writes the WHOLE page document at once.' The word WHOLE plus 'a block you leave out is deleted' makes the replace semantics unambiguous and distinguishes it from partial-update siblings. It also names get_page as the paired read tool.

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 an explicit workflow: call get_page first, edit what it returned, send the version it gave you. It explains why (stale writes fail loudly) and covers the image-handling case, so the agent knows both when to use it and what prerequisites to satisfy.

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