table_table_filter

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

No annotations are provided, so the description carries the full burden. It indicates read-only behavior (filtering, no modification) and output format. However, it omits potential behaviors like file not found errors, performance characteristics, or handling of large files. The description is adequate but not comprehensive.

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 extremely concise: two sentences that front-load the core action and then provide operator details. Every sentence adds value without redundancy.

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?

Given the tool's simplicity (4 required params, no enums, straightforward operation), the description covers the essential aspects: supported file types, operation, operators, and output format. Some details are missing (e.g., filepath resolution), but the tool is still usable. The description is nearly complete.

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 0%, so description must compensate. It lists operators and file type (CSV/TSV). While this adds meaning beyond raw schema, it lacks details on filepath format, column naming conventions, and operator case sensitivity. It partially compensates but leaves room for ambiguity.

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 clearly states the action (filter), target resource (rows in a CSV/TSV file), output format (JSON array), and lists available operators. It distinguishes itself from sibling table_ tools like aggregate, columns, read, write by specifying filtering behavior.

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 implies usage for filtering but offers no explicit guidance on when to use this tool versus alternatives (e.g., table_table_read for full data, table_table_aggregate for summaries). No exclusion criteria or prerequisites are provided.

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