Trace formula

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description does add one genuine behavioral detail — `more`: results left out, implying truncation — but otherwise adds little about auth, limits, or evaluation behavior.

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?

It is short, but the structure is awkward: a cryptic first clause followed by a bare list of output keys. The content is front-loaded only in the sense that it is brief, not that it prioritizes the most decision-relevant information.

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?

An output schema exists, so explaining return fields (cells/unknown/steps/more) is largely redundant, while the description omits the actual tracing semantics and leaves two required parameters undocumented. For a 5-parameter, 3-mode tool, this leaves the agent under-informed.

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 60% (path and sheet undocumented), which sits between the high and low baselines. The description's terms (cells, unknown, steps, more) map to output fields rather than the path/sheet/all_levels inputs, so it does not compensate for the coverage gap.

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 opening 'Audit formulas, calculated here' is vague and never states that the tool traces precedents, dependents, or evaluates formulas — that meaning only surfaces in the schema's `direction` enum. The name 'trace_formula' conveys more than the description, which spends most of its words on output keys rather than the tool's action.

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?

There is no statement of when to use this versus siblings like read_range, find_cells, or goal_seek, and no mention of prerequisites such as needing a loaded workbook. The `direction` modes imply some usage but the description never routes the agent.

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