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

Beyond the readOnlyHint/openWorldHint annotations, the description discloses the most decision-relevant behavior: result caps (25 rows), time window (30 vs 120 days), and the credit cost of full=true with an alternative free path via a watch. It does not describe ordering, pagination past 25 rows, or what happens when a state has no gaps, but the cost/limit disclosure is substantive.

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 front-loaded sentences: the selection criteria and returned columns come first, the pricing/limits second. Dense but every clause carries information; the only slight drag is the pricing parenthetical inside the same sentence as the result definition.

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?

No output schema exists, and the description does name the returned fields and access limits, which covers a lot. Still, for a three-parameter filtered-list tool with zero schema documentation, the unexplained alert values are a real gap an agent could trip on when invoking it.

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 0%, so the description must define all three params. It handles full well (whole 120-day window, cost model) and glances at state ('with a watch for that state'), but the alert enum values new_desert, lost_last_bank, and down_to_one_bank are never mapped to the three gap categories described, leaving the agent to guess which enum matches 'no bank' vs 'one bank'.

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?

Names a concrete resource and its selection criteria: 'ZIPs where a branch closing left no bank, one bank, or a 10+mile trip to the next branch', and states what each row contains (the bank that left, the nearest one still open). That is more specific than most list tools, though it does not explicitly distinguish itself from the sibling list_gaps or list_places.

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?

Usage context is implied through the free/paid split ('Free: the last 30 days, 25 rows', full=true costs 100 credits), which tells the agent when the cheap call suffices. However there is no explicit statement of when to pick this over list_gaps, get_bank_access, or order_bank_report, and no exclusion guidance.

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