Canvas skeleton

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

Although readOnlyHint is already set, the description adds real behavioral context: the exact return payload, the 20-event default window, the incremental since mechanism with lastSeq, and the cost of includeSettings ('more tokens'). The rule 'This is the only source of element IDs besides create results — never invent IDs' is a valuable operational constraint that no annotation conveys.

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?

Dense but front-loaded: the return payload comes first, then ID guidance, then parameter-specific advice. The sentences are long, and the field list could be shortened, but every clause carries useful information and no words are wasted.

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?

No output schema exists, yet the description fully documents the returned structure, selection, nodeCount, recent events, and lastSeq. Combined with the alternative to inspect_element and the ID-safety rule, an agent has everything needed to call it correctly.

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%, which sets the baseline at 3, but the description adds meaning the schema lacks: the default event window when since is omitted, the convention of passing the prior lastSeq, and the token cost of includeSettings. Only maxDepth is glossed generically ('limits nesting for very large pages').

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?

Opens with a specific verb and resource: 'Return the compressed element tree of the open document', then enumerates the node shape and metadata returned. It is clearly distinguishable from siblings, since it explicitly hands single-element reads to inspect_element.

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 alternative ('use inspect_element for a single element instead') and explains when to pass since versus relying on the default 20-event window. It has no explicit exclusions, so it falls just short of the top score.

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