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

Goes well beyond the annotations (which only say non-readonly, non-destructive, non-idempotent, open-world) by disclosing that sum checks are performed and flagged, unreadable cells are surfaced, values are copied and never invented, and generated files are retained only 24 hours — exactly the retry/expiry context an agent needs given non-idempotency. It also reveals the multi-format output (rows/columns, totals, CSV text, links).

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 trigger condition is front-loaded and the exclusion is last, which is good ordering. The second sentence is a long run-on enumerating seven return elements, much of which duplicates the existing output schema, so it is slightly heavier than necessary.

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 tool with nested input objects, four params, annotations and an output schema, the description covers triggering, input selection, exclusions, and the non-obvious behaviors (24-hour retention, no-invention guarantee). The exhaustive return enumeration is partly redundant with the output schema, which is the only real slack.

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 100%, so the baseline is 3; the description earns above that by telling the agent that exactly one of file / image_url / image_base64 must be supplied and by prescribing when to add hint ("when the user says which columns they want"). It does not restate size/format limits, but those are already 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?

States a specific transformation (photo of a receipt/notebook/timesheet → table/spreadsheet) with a concrete list of source artifacts, so the agent can instantly match the user's situation. The photo-input framing cleanly separates it from the modality siblings text_to_sheet and voice_to_sheet without needing to name them.

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?

"Use this when the user has a photo of ... and wants it as a table" gives an explicit trigger, and "Not for photos of people or scenery" gives an explicit exclusion. However, it never names the sibling tools (text_to_sheet, voice_to_sheet) or states the condition that would route to them, so the alternative selection is only implied by modality.

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