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

With no annotations provided, the description carries the full burden and delivers richly: it discloses default limit (50), max cap (200), window semantics (server filters on creation timestamp), response echo of a window block, precedence of `range` over `from`/`to`, deprecation of `offset`, retirement of legacy range values with effective date, hard cap on range windows (400 days), and the supported pagination path via cursor. This far exceeds typical behavioral disclosure.

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?

The description is compact and front-loaded: opening verb+object phrase, then limits, filters, window semantics, and ending with a useful return-field note. Every sentence adds value. A tiny deduction for density—the final parenthetical list is long—but it's information-dense rather than padded.

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 13-parameter list endpoint with no output schema and no annotations, the description is remarkably complete. It covers defaults, pagination, deprecation, date semantics, and return-field context. It doesn't explain the sort default or all 13 parameters explicitly, but with 92% schema coverage the schema handles those, and the description covers the high-risk behavioral aspects.

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 92%, so the schema does most of the work. The description adds meaningful cross-parameter context: how filters combine, window behavior, `range` precedence, legacy value retirement, and the `next_cursor` pagination path. It even identifies which market rows include DRM and oracle pricing fields, adding value beyond individual parameter descriptions. Minor deduction for not enumerating every filter parameter, but it names the important ones.

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?

The description opens with 'Filtered deposit list. Deposit search.' which clearly identifies the tool's function as listing/searching deposits with filtering capabilities. It distinguishes itself from siblings like get_deposit (single deposit) and list_activity/list_intents by explicitly scoping to deposits and describing specific deposit-centric filters (depositor, delegate, platform, currency, date window).

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 clearly states usage context: filters are optional, empty query returns a bounded page, and specifies default/max limits. It explains when to use date windows and how filters combine. It doesn't explicitly contrast with alternatives, but the sibling differentiation (deposit-specific filters vs get_deposit's single-item lookup) makes the when-to-use fairly clear.

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