Get Workflows

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

Annotations already carry readOnlyHint=true and openWorldHint=false, and the description adds substantial context beyond them: 'reads nothing, changes nothing' reinforces the safety profile, and the disclosure that COM-tier unshipped tools are 'marked forthcoming rather than pretended present' is a genuinely valuable honesty guarantee — the agent learns it will not be handed fabricated tool names. The enable_tools/lite pack dependency is also disclosed.

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?

Four dense sentences, each earning its place: output structure, invocation modes with concrete values, truthfulness policy, and safety note. The length is justified by the two-mode invocation and the honest-disclosure clause; it is front-loaded with the core purpose. Not a 5 only because it is somewhat long, but nothing is 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?

With no output schema, the description must convey return behavior — and it does: a task list or a step-by-step recipe with notes. It covers all invocation modes, all valid parameter values, the pack/enable_tools dependency, the no-mutation guarantee, and the forthcoming-tools policy. Nothing an agent needs to call it correctly is missing.

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 carries the full burden — and it fully compensates. It explains that the task parameter takes no value to list tasks or a named task for a recipe, and enumerates every valid value (merge-workbooks, report-build, data-cleanup, formatting-audit-and-fix, safe-edit-of-rich-workbook, migrate-from-incumbent), effectively supplying an enum the schema omits.

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 states a precise function: returning recommended tool sequences for multi-step spreadsheet tasks, each with the tool name, rationale, and pack. It clearly distinguishes itself from the ~40 operational siblings (read_range, write_range, set_cell, etc.) by being the only guidance/metadata tool, so an agent can separate it from the others without inspecting 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?

The description gives explicit invocation patterns for both modes — call with no task to list available tasks, call with task='<name>' for a recipe — and enumerates all six valid task values. It provides clear context, but stops short of explicitly naming alternatives or stating when-not-to-use; the differentiation from operational siblings is implied through the tool's nature rather than stated.

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