Sample Table Data

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

Annotations are absent, so the description carries the full burden of behavioral disclosure. It discloses that only a small sample is returned, that rows come as a markdown table, and that sample_size defaults to 10 and is server-capped. However, it doesn't state whether the sample is deterministic/random, whether the operation is read-only (though 'retrieves' implies so), or how errors like non-existent tables or permission failures behave. Adequate but not complete.

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?

Two sentences, no filler. The main purpose and output format are front-loaded; the parameter behavior follows in the second sentence. Everything present contributes necessary information, and no word is wasted.

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 an output schema available and a simple two-parameter input, the description covers the core behavior, sample mechanism, output format, and the default/cap behavior of sample_size. It is complete enough for an agent to successfully call the tool for a quick preview. The only missing-piece is a clarification about how this differs from execute_query when both could return rows, but that is more of an usage guideline than a completeness gap.

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 0%, so the description must compensate. It clearly defines sample_size's effect ('controls how many rows to return'), the default (10), and server cap. It correctly identifies table_name as 'the specified table'. This adds meaningful semantics beyond the bare integer/string types. Slight gap: it does not specify table_name formatting or whether sample_size is inclusive or capped at a hard maximum.

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 states a clear, specific action ('Retrieves a small sample of rows'), names the resource ('from the specified table'), and specifies the output format ('compact markdown table'). This is distinct from siblings like list_tables (lists table names), get_table_details (metadata), and profile_table (statistics); even execute_query is clearly different in scope ('a small sample' vs arbitrary query results). There is no ambiguity about what the tool does.

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 quick data previews but does not explicitly say when to choose this over execute_query or get_table_details. It states that sample_size is capped by the server, but it does not provide scenarios or compare to full-query retrieval, leaving the 'instead of' guidance to inference.

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