Delete a text range

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

The description goes well beyond the annotations: it discloses that deletions are irreversible, that indexes shift after every delete, that deleting a trailing newline merges paragraphs, and that the tab's final newline cannot be deleted. These are critical behavioral details not captured by destructiveHint or readOnlyHint.

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?

The description is compact and front-loaded with the core operation, then packed with only high-value caveats. Every sentence contributes unique operational information, with no filler or repetition of schema content.

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 mutation tool with no output schema, the description covers the full set of needed constraints: valid range contents, table boundary restriction, index refresh requirement, shift behavior, merge behavior, an exception, and irreversibility. An agent has enough information to invoke this tool correctly and safely.

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 input schema already documents all five parameters with 100% coverage. The description adds useful context about start/end index semantics and indexing shifts, but it does not substantially clarify tab_id, segment_id, or document_id beyond what the schema already states. Baseline 3 is appropriate.

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 clearly states the operation ('Deletes the content in [start_index, end_index)') and the resource type (text range), and adds concrete scoping details like inline images, whole tables, and the table-cell-boundary restriction. This makes it easy to distinguish from sibling edit tools like insert_text or replace_range.

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 explicit operational guidance: fetch fresh indexes from read_document_text first, index shifting behavior, the final-newline exception, and the no-undo warning. It does not explicitly name an alternative tool for delete-like operations, but the prerequisite and exclusions are clear enough for correct use.

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