docs_edit

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

With no annotations, the description carries the full burden and does disclose real behavior: steps execute in order within a single tab, and the result reports each step plus whether Drive reflects the change — useful evidence that effects are verified rather than assumed. It omits auth/prerequisite context (whether the doc must be open in a browser) and how a failed lookup behaves, which is a notable gap for a live-editor mutation tool.

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?

Three sentences, front-loaded with the mechanism and the routing rule; the capability list in sentence one is long but mostly load-bearing. Some of the enumerated actions duplicate the nested schema's own 'One action. Selection: … Changes: …' summary, which is mild redundancy rather than padding.

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 complex, 60-step-capable scripting tool with no output schema and no annotations, the description covers identity of the resource, execution semantics, routing, and the shape of the result, which is what an agent needs before calling. Remaining unknowns — failure handling on unmatched find/section, and whether steps are atomic or partially persisted — are left unaddressed.

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 67% and the description adds meaning beyond it by organizing the action model (selection vs. change steps) and flagging non-obvious mechanics such as Tab moving between table cells when the schema only lists Tab as a key. It stops short of explaining ordering/interaction rules between steps, which the schema hints at but never fully defines.

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 (edit) plus the distinctive mechanism: a sequence of human-like steps driven in the real editor, with an explicit inventory of the step types (find/caret/select/extend/section/insert/text/delete/key/menu/format/undo). It also names the siblings it is not (docs_write/docs_format), so an agent can route without opening schemas.

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 selection rule: use it for anything docs_write/docs_format do not cover, then enumerates the concrete gaps (table rows and columns, page breaks, table of contents, headers), which is effectively the when-not rule inverted. The alternative tools are named rather than implied.

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