get_rows

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

Annotations already declare readOnlyHint=true, and the description adds value by disclosing SQL parameterization (no injection) and noting that column projection reduces token usage significantly. This provides useful behavioral context beyond the annotation, though it doesn't describe pagination or redaction behavior.

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 with the core purpose, then efficiently adds security, operator list, projection tip, and aggregate alternative in only five short sentences. No redundancy or 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 tool with 10 parameters and no output schema, the description covers the essential usage: filters, operators, projection, and when to prefer aggregate. It could mention pagination defaults or redaction, but those are documented in the schema, so the description is adequately 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 100% with all parameters described. The description enhances this by explaining the operator set (eq, neq, gt, etc.), emphasizing the token-reduction benefit of columns=[], and noting the SQL-parameterization security aspect. This adds meaning beyond the schema's descriptions.

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?

Description clearly states 'Filtered row retrieval via structured filters' with a specific verb and resource. It distinguishes itself from aggregate() by suggesting aggregate() for summaries, and the sibling context includes many related tools, but this description scopes the tool's function precisely.

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 provides explicit guidance to prefer aggregate() for summaries instead of paginating through rows, and advises using columns=[] for projection on wide tables. However, it doesn't explicitly mention alternatives like sample_rows or search_data, so there is room for more exclusion guidance.

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