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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description's 'without mutation' is consistent but not novel. However, it does add behavior beyond annotations by specifying that the preview covers trim/extend and split operations, which are concrete, non-obvious capabilities. No contradiction exists.

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?

Two short sentences, front-loaded with the critical 'without mutation' qualifier. Every phrase adds value—the first sentence establishes the read-only nature, the second enumerates supported operations. No wasted words.

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?

Given the tool's moderate complexity (two operation variants), the presence of a detailed schema with oneOf, an output schema, and annotations covering safety, the description is sufficiently complete. It captures the essential behavioral contract (preview-only) and lists all supported operations; any remaining details are handled by the schema and annotations.

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?

The schema already provides descriptions for projectId and expectedRevision, but the operation parameter has no description and is expressed as a oneOf with const values. The description's enumeration of 'trim or extend' and 'split' maps to the two operation variants, but it does not clarify parameter semantics like 'expectedRevision' or delta meanings beyond what the schema names imply. With 67% schema coverage, the description gives partial compensation.

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 opens with 'Preview without mutation,' using a specific verb and resource that immediately distinguishes it from the sibling 'timeline_edit_apply.' It then enumerates the exact operations ('Trim or extend one timeline item,' 'Split one timeline item at an exact sequence position'), making the tool's scope unmistakable.

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?

'Preview without mutation' clearly signals that this tool is for pre-flight checks rather than actual edits, and the sibling 'timeline_edit_apply' implies the alternative. However, it never explicitly states 'use this instead of timeline_edit_apply when you want to verify without persisting changes,' so it falls short of a fully explicit when/when-not directive.

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