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

Annotations only declare readOnlyHint=false and destructiveHint=false, so the description carries the real burden and does it well: partial success, dedup-by-name matched rather than double-added, blank-field fill-only, per-row refusals isolated in errors, and error=true only when nothing was created or matched. The only gap is that side effects on matched records (which blank details get written) are described only loosely.

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 purpose, batch limit, and the return shape, then behavior, then the confirm requirement, then the alternative. It is dense but every sentence carries a distinct fact; the return-object rendering makes one sentence heavier than it needs to be.

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 single-parameter bulk-write tool with no output schema, the description supplies what is missing: batch ceiling, what the returned object contains, how matched versus created versus refused rows differ, and the human confirmation step. Nothing an agent needs to invoke it correctly is absent.

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 100%, so the nested row fields are already fully documented. The description adds operational meaning by framing items as file-ordered rows and by explaining that `line` is echoed into results so a refusal can be traced back — useful, but the bulk of parameter meaning already lives in the schema, so baseline applies.

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?

Opens with a specific verb and resource plus scope: "Create many customers from a list", and immediately names the sibling workflow it pairs with (read_file_rows) and the sibling it is not (save_client for changes). An agent can distinguish it from list_clients and save_client without opening any schema.

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 explicit routing: use save_client to change an existing customer, call again with the next page beyond 100 rows, and show a preview plus get one confirm before calling. That is a when-to-use, a when-to-use-differently, and a prerequisite in three sentences.

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