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

Annotations already declare readOnlyHint, idempotentHint and non-destructive, so safety is covered; the description adds real behavioral context beyond them: result ordering (newest first), the presence of a pending-review bucket including extra pulls and pulls after payoff, the last bank sync timestamp, and an explicit sign-in prerequisite. This is meaningfully more than the annotations provide, though it does not state pagination limits or what happens when no bank feed is connected.

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?

One front-loaded sentence with the resource and ordering up front and the auth requirement last, with no filler or repetition of the title. The parenthetical clause list ('including extra pulls and pulls after payoff') is dense but each element adds information about what the review bucket contains.

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, the description steps in to describe return content (matched debits, pending-review debits, last bank sync) and ordering, which is exactly what an agent needs to decide whether to call it. The auth precondition is stated; only edge behavior (empty feed, pagination) is unaddressed, which is minor for a read-only single-parameter tool.

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% and the single 'days' parameter is fully documented in the schema with bounds and default, so the description carries no obligation here. The description says 'recent' without ever tying it to the days window, adding no meaning beyond the schema; baseline 3 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?

Names a specific verb and resource ('List recent funder debits from the signed-in user's connected bank feed') and enumerates the two result categories: advance-matched debits and unreviewed funder-like pulls. It never names the sibling get_my_upcoming_debits, which is the closest alternative, so differentiation is implied by 'recent' rather than stated.

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 word 'recent' plus the mention of the last bank sync gives an implicit cue that this covers past/synced activity as opposed to the upcoming view, but there is no explicit 'use this when...' statement and no exclusion pointing at get_my_upcoming_debits or list_my_alerts. An agent can infer the usage context but must compare sibling names itself.

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