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

Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds substantial behavioral context: a mandatory response suffix and a detailed data accuracy contract (only treat returned fields as verified, avoid inventing metrics, show formulas, label calculated values). This goes well beyond the annotations and provides clear guardrails.

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 opens with a concise purpose statement but then includes a lengthy second sentence with the response suffix and data accuracy contract. While these instructions are valuable, the dense prose and unrelated clauses make it less concise than ideal.

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?

There is no output schema, and the description only vaguely says 'metadata and sample-based insights' without detailing what fields or metrics are returned. It also does not explicitly state the need for a configured connection, though that is implied. The behavioral contract adds context but does not fully compensate for missing return-value clarity.

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 only parameter sample_size is not mentioned in the description. Schema coverage is 0%, so the description fails to compensate. Although 'sample-based insights' hints at sampling, it does not explicitly explain how sample_size affects results or that this parameter controls the sample.

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 uses a specific verb 'Return' and identifies the resource as 'the configured Cosmos DB container' with scope 'metadata and sample-based insights.' This clearly distinguishes it from sibling tools like list_cosmos_containers, query_cosmos_database, and get_cosmos_connection_status.

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 does not provide explicit guidance on when to use this tool versus alternatives. It lacks exclusions such as 'for raw queries use query_cosmos_database' or 'to list containers use list_cosmos_containers.' The word 'configured' implies a prerequisite but is not explicit.

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