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

With annotations only declaring readOnly/destructive/idempotent flags, the description carries real weight: duplicates block the entire output, unmatched records are reported even when excluded, missing-side fields become empty strings, and size limits (1 MB/10,000 records/250,000 cells) plus one-operation cost and an uncharged size error are disclosed. Silent truncation is explicitly ruled out.

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-loaded with purpose, then progressively discloses constraints and limits. Dense but every sentence carries operational information; slightly long, yet nothing reads as 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?

For a compute tool with no output schema and no top-level param descriptions, the description covers inputs, output shape (row lineage, empty missing-side fields, value_changed warnings), limits, and idempotency. An agent has enough to invoke it correctly without further documentation.

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?

Top-level schema description coverage is effectively absent, so the description compensates by explaining key semantics (non-empty unique keys, duplicates block output), retention mode meaning, and compare fields as warning-only. It adds genuine meaning beyond the schema, though it does not detail every nested field such as output_delimiter or spreadsheet_safe.

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 opening sentence states a specific verb and resource ('Join two bounded tables using exact string or composite keys') and immediately bounds the technique. Combined with sibling names like clean_csv, inspect_table, and prepare_table, an agent can tell this is the reconciliation/join tool, not a cleaning or inspection tool.

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?

It gives clear operational context: choose left/inner/full explicitly, reuse request_id for identical retries, and rules out fuzzy matching or destination writes. It does not name alternative sibling tools or state when-not to use this one, so it stops short of the top tier.

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