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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered. The description earns credit by adding substantive behavioral context beyond that: missing rows are never coerced to zero, and returned content includes missing-row status, ranking, coverage, and provenance, plus an explicit scope caveat (point-in-time balances are not daily flows or wrongdoing evidence).

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-loads the core comparison purpose, then the returns, then the scope caveat. Dense but every clause carries information; only the closing disclaimer slightly pads an otherwise tight 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?

With no output schema, the description compensates well by enumerating the return shape (quantities, missing-row status, issuer labels, ranking, coverage, provenance) and the missing-row handling rule. Combined with full schema coverage and rich annotations, an agent has enough to call it correctly.

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%, so the schema already documents symbols (2-8 unique exact tickers), response_format (markdown/json), and settlement_date (YYYY-MM-DD, hot window). The description's 'two to eight' simply restates the schema bounds and adds no new parameter semantics, so 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?

States a specific verb (compare), resource (SEC fails-to-deliver balances), cardinality (two to eight tickers), and constraint (same settlement date, self-hosted official snapshot). It is immediately distinguishable from siblings like sec_ftd_latest, sec_ftd_history, sec_ftd_top, and sec_ftd_search_securities by its comparison scope.

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?

Provides concrete example utterances ('compare GME, AMC, and TSLA FTD balances', 'which selected symbol had the largest published balance on 2026-08-14?') that make the intended use clear. However, it never names the alternative tools (e.g. sec_ftd_latest for a single symbol) or states when not to use it, leaving routing to inference.

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