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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds per-operation return summaries, but says nothing about pagination, result limits, or whether a nonexistent prompt_id errors or returns empty. With output schema present, the return summaries add limited unique value.

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 numbered operation list is front-loaded and scannable, with parameter recipes ahead of return summaries. Two lines are spent restating return values already captured by the output schema, which is minor waste but not harmful.

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 5-parameter tool with zero schema descriptions, the operation recipes make it callable without guesswork. Remaining gaps are the is_custom vs prompt_type='custom' redundancy and no guidance on cross-tool selection; return values need not be covered since an output schema exists.

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 carry the full burden — and it largely does, mapping every parameter to concrete operation combinations (prompt_id, is_custom, workspace_id, prompt_type). The gap is that 'prompt_type' is only ever shown as 'custom' and its relationship to the overlapping 'is_custom' boolean is unexplained, leaving genuine ambiguity.

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 names a specific resource (BigQuery prompt catalog) and enumerates the exact operations available via the 'request' enum. An agent can distinguish 'menu' from 'prompt_details' immediately. It does not distinguish itself from siblings like query_contexts or query_data, which is the only gap.

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?

Each of the four operations carries an explicit parameter recipe (e.g., request='menu', prompt_type='custom', workspace_id=<int>), which tells the agent precisely which combination to supply. It stops short of saying when this tool is preferable to query_data/query_contexts, or whether a menu call must precede a details call.

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