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

Adds substantial context beyond annotations: header matching rules, that unknown headers are listed and skipped, all-or-nothing validation ('nothing is added if one is wrong'), and per-row cost with a free no-op case. None of this is in the annotations (readOnly=false, destructive=false, idempotent=false), and none of it contradicts them.

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?

Front-loaded with the core action, then alternative mode, then safety and cost. Efficient, but the nested parentheticals make one dense run-on paragraph that takes a second pass 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?

With no output schema and a mutation tool, the description covers the important behaviors: header handling, atomic validation, and cost. Gaps remain around the outcome (row count reported?), where file_id comes from (files_upload), and the mutual exclusivity of table/new_table.

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 only 33%: only 'table' is documented in the schema, and even that lacks meaning for 'new_table' and the required 'file_id'. The description partially compensates by explaining new_table's effect and that file_id refers to a CSV in the file store, but it never clarifies that table vs new_table are alternatives or what happens if both/neither are supplied.

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 action on a specific resource: rows from a CSV in the file store, into either an existing table or (via new_table) a new one. The two-mode structure is clear. It does not distinguish itself from similarly named siblings such as import_csv or import_status, which an agent will likely hesitate between.

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?

Implies clear usage routing: pass 'table' to append to an existing table, or 'new_table' to create one with a text column per header. Nothing says when not to use it or points to import_csv/import_status as alternatives for other import paths.

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