Recipes Inspect Table With Sample

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds the useful fact that this is a composite operation returning schema plus sample data. It doesn't state auth requirements, result size limits, or that the call may read actual row data from a live table, which matters for a tool with openWorldHint=true.

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?

A single front-loaded sentence that names the composite operation before the details. No filler, though 'Composite recipe:' is slightly internal jargon that a first-time agent must parse. Efficient overall.

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 and annotations cover safety, so the description needn't explain return values or read-only behavior. However, for a multi-parameter composite it leaves out parameter semantics (sample_rows count) and sibling differentiation, both of which an agent needs to choose and invoke it correctly.

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 75%, below the high threshold, so the description should compensate but says nothing about parameters. 'Preview sample rows' only hints at sample_rows, and neither the default count (5) nor the meaning of the count is clarified. The database/schema_name qualification described in the schema is not echoed or expanded in the description.

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 ('describe', 'preview') and resource ('table'), and enumerates what comes back: schema, row count, column types, sample rows. The 'Composite recipe ... in 1 call' framing signals it bundles two operations. It never names the siblings it replaces (tables_describe_table + tables_sample_table, or recipes_profile_table), so an agent must infer the distinction.

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 phrase 'in 1 call' implies the tool is for when you want both schema and a sample together, but there is no explicit when-to-use, when-not-to-use, or named alternative. Nothing tells the agent whether to prefer this over calling tables_describe_table and tables_sample_table separately, or over recipes_profile_table.

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