text

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

With no annotations, the description carries the full burden, and it does disclose one important trait: all edits happen in a single undoable batch, and replace preserves mixed formatting rather than flattening it. That is real behavioral value. It does not disclose failure modes, what happens when an id is missing, how expected_revision conflicts are handled, or whether the caller needs any permission.

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 batch/undo framing is front-loaded in the first clause and the two payload shapes follow immediately with compact inline examples. Every sentence carries information; the only mild cost is the dense bracket-notation that takes a moment to parse.

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 annotations and no output schema, the description covers the core edit semantics well but leaves two parameters (show, expected_revision) and the return value completely unaddressed. An agent could construct a basic call from it but would be guessing on concurrency and preview behavior.

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 description coverage is 0%, so the description must compensate, and it does for two of the four parameters: the exact shape of edits ({id, text} with \n for newlines) and replace ({old, new, ids}) is spelled out with examples, including that ids scopes the swap. The show and expected_revision parameters get no mention at all, leaving the optimistic-concurrency contract unexplained despite being named in the schema.

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 does state a concrete action ("change text in one undoable batch") and distinguishes two operating modes, edits vs replace, with inline payload examples. But the resource is only "text" with no indication of what object type or document the text belongs to, and the tool name itself ("text") conveys nothing on its own. An agent gets the mechanism but not the target domain.

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 distinguishes the two internal modes (whole-value replacement via edits vs substring swap via replace) and notes replace preserves mixed formatting, which is genuinely useful selection logic. However, there is no guidance on when to use this tool rather than siblings such as style, attributes, insert, or structure, and no prerequisites or exclusions are stated.

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