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

With no annotations, the description carries the full behavioral burden and does well: it discloses that selected rows are sent to the tenant's own model endpoint, that the answer reports row and byte counts, and that prepare:true performs a dry run. It does not cover permissions or failure modes, but it is substantially more transparent than typical unannotated tools.

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 dense but front-loaded with the core purpose, then layers the selection modes, egress behavior, and dry-run behavior. It earns its length, though the long compound sentence structure makes it somewhat harder to parse than it could be.

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 7-parameter tool with no output schema and no annotations, the description covers the important operational context: input mode choice, external model endpoint behavior, evidence/count reporting, orchestrator fallback, and dry-run preview. It is quite complete, though it could say more about return shape or permission prerequisites.

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 71%, so a baseline of 3 applies, but the description adds meaning by explaining the relationship between sql and collection as alternative selection modes and clarifying that prepare:true returns what would be sent without sending it. It leaves k, property, params, and question to the schema, which is acceptable given the decent coverage.

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 action: answering a question from the data with evidence, using either a SQL statement or a collection search. It is clear what the tool does, but it does not explicitly differentiate itself from the sibling 'query' tool, so it falls short of a 5.

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?

It gives clear usage context: provide either a row-selecting statement or a collection to search, and use prepare:true to preview without sending. It also notes the orchestrator/assistant alternative inside the deployment. However, it does not explicitly state when to prefer this over the sibling 'query' tool.

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