get_table_schema

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

With no annotations, the description carries the transparency burden. It discloses important behavioral traits: short-name matching and case-insensitivity, 'Row data is never included,' and the DynamoDB costSignal note. The word 'Returns' plus the explicit exclusion of row data strongly implies a read-only operation. However, it does not explicitly state the snapshot/staleness behavior (which appears only in the schema's maxAgeSeconds description) or what happens when a table is not found. These minor omissions prevent a 5.

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 concisely written and front-loaded: the first sentence states the core purpose and contents, followed by naming behavior, usage guidance, exclusions, and a final note. Four sentences cover everything without redundancy or filler. Each sentence earns its place.

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 no output schema and moderate complexity, the description is remarkably complete. It covers what the return value includes (columns, keys, indexes, DynamoDB billing mode, estimated counts), the naming behavior, usage context, exclusions (no row data), and a system-specific detail (costSignal). The parameter schemas supply the remaining operational details, leaving no significant gaps for an agent to make a correct selection or invocation.

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?

The schema already describes both parameters (100% coverage), so the baseline is 3. The description adds meaning beyond the schema for `tables` by specifying 'Accepts short names ("orders" matches "public.orders") and is case-insensitive.' This is extra semantic value. It does not describe `maxAgeSeconds` in the main description, but the schema does, and the description's added naming behavior justifies a 4 rather than a 3.

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 tool's function: 'Returns the full schema for specific tables or collections by name' and enumerates the included elements (columns, data types, nullability, primary keys, foreign keys, indexes, DynamoDB keys/billing mode, MongoDB counts). It also distinguishes from siblings via explicit comparisons: 'instead of pulling every schema with get_graph_summary' and 'Do NOT call for a table inventory; use get_infra_overview for that.'

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 gives explicit when-to-use guidance: 'Call this after get_infra_overview when you need column-level detail to write a SQL query, DynamoDB expression, or MongoDB filter for specific tables.' It also clearly states when not to use it and the alternative: 'Do NOT call for a table inventory; use get_infra_overview for that.' It even points to an alternative for broader schemas: 'instead of pulling every schema with get_graph_summary.'

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