Import Uber Gmail

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

Annotations say readOnlyHint=false, destructiveHint=false — a writes-somewhere-but-not-destructive operation. The description adds valuable behavioral detail: idempotency, the exact upsert target and source key format, and cost/auth requirements ($0.15, API key). It stops short of describing rate limits or conflict behavior on re-runs beyond 'idempotent'.

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?

Two dense sentences, front-loaded with the action and target, cost/auth in parentheses at the end. Every phrase carries information; nothing is wasted, though the parenthetical is terse.

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?

Output schema exists so return values needn't be explained. For a 7-param write tool, the description covers the critical behavior (idempotency, write target, cost, auth) but leaves several params and the dry_run control unexplained.

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 43%, so the description compensates partially by naming dry_run, max_results, query, account. But email, request_id, and idempotency_key are not covered, and dry_run's semantics (preview without writing) are not explained.

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?

Specific verb (search) + resource (Gmail for Uber receipts) + explicit write target (log_place_visit rows with sources gmail:uber-{gmail_id}). Directly distinguishable from sibling import_venmo_gmail and search_gmail.

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 implies this is for Uber-receipt ingestion and mentions 'optional dry_run' but does not state when to prefer search_gmail / read_gmail_message / log_place_visit directly, nor when to use dry_run vs a real run.

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