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

Annotations already declare a read-only, idempotent, closed-world read, so this description clears the lower bar easily by adding substantial context: exactly what the detailed response contains (source tool, call parameters, row count, creation and expiry times, column schema, and unit/basis for amount/ratio/count columns), what the list-mode response contains, ordering (newest first), and page size (50). It also discloses the expiry behavior and the unauthenticated-canvas listing limitation, none of which is in the annotations.

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?

Information is front-loaded: the source and identity of the dataframes come first, then the two modes, then the SQL-prep guidance, then the deployment caveat. The prose is dense and runs as one long paragraph, which slightly hurts scanability, but nearly every clause carries operational information rather than filler.

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?

An output schema exists, yet the description still tells the agent what each mode returns and when to prefer which, and covers the unusual deployment case. For a two-mode read tool with defined lifecycle semantics (expiry), nothing needed to call it correctly is missing.

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 100%, so the schema already documents both parameters, but the description adds operational meaning: the name comes from a dataset field and unlocks the full detail view, while offset is passed as next_offset from the prior page and is ignored when name is set. That cross-parameter interaction is a genuine addition beyond the schema.

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+resource (describe df_<id> dataframes) and precisely names where they come from: staged by fdic_query_financials/fdic_get_deposits on oversized offset-0 results, or saved via fdic_dataframe_query's register_as. It also distinguishes the two modes (named describe vs. unnamed list), so an agent can tell it apart from the sibling query tools without opening a schema.

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?

Gives explicit when-to-use (read a table's columns this way before writing SQL for fdic_dataframe_query), how to choose between the two modes (pass name vs. omit name), and a concrete deployment exclusion: on unauthenticated HTTP where all callers share one canvas, listing is unavailable, so pass the name from a dataset field. Nothing is left to inference.

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