Describe a table or view

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. Because no output schema exists, the description's disclosure of what is returned (field list, row count, and view SQL for views) carries real behavioral weight that the structured fields do not provide. It still omits error behavior (e.g. unknown table) and whether the row count is metadata-derived or a scan.

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 states the resource first and then the returned artifacts, with no redundant or filler text.

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 simple read-only metadata lookup with no output schema, the description covers the essential return shape (fields, row count, view SQL) and the schema covers all inputs. Only edge-case behavior (missing table, permission failures) is absent, which is a minor 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 100%, with each of table_id, dataset_id, and project_id documented in the schema (including the config default for project_id). The description adds no parameter-level detail beyond that, so the baseline 3 applies.

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 specific verb ('Show') and resource (fields of a table or view), plus the extra returns of row count and view SQL, which clearly separates it from siblings like list_tables (enumeration) and run_query (execution). It never explicitly names a sibling, but the scope is unambiguous.

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?

There is no statement of when to use this tool versus alternatives such as run_query or list_tables, and no prerequisites (e.g. that the dataset/table must already exist, or that this is the inspection step before querying). Usage is only inferable from the tool name and the described output.

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