describe_table

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

Annotations already declare readOnlyHint=true, and the description does not contradict that. It adds useful behavior beyond annotations: system columns are hidden by default unless include_system_columns=true, and full=true adds extra detail. It also discloses source flexibility for solution files vs. canvas app cached schemas.

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?

Dense but efficient: the primary output fields are front-loaded, optional toggles are explained, and source variants are noted. It is close to a 5, but the packed phrasing around source/app/table may require careful parsing.

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 no output schema, the description compensates well by listing what the tool returns, including columns, types, requiredness, etc. It covers most invocation concerns, but the app parameter and the exact acceptable values for source remain slightly ambiguous.

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 carries the full parameter burden. It meaningfully explains table as logical/display/entity-set name, describes source inputs, and clarifies full and include_system_columns. However, the app parameter is not explicitly described, so one of five params remains under-specified.

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 object of interest ('columns of one table') and enumerates the exact kinds of metadata returned. This clearly distinguishes it from sibling tools like list_tables or list_relationships, even without naming them.

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?

Describes when the tool is relevant: a single table's schema from a solution or canvas app, with optional modes for system columns and full metadata. It does not explicitly name alternatives or state when not to use it, but the 'one table' scope makes the context clear.

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