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

Annotations indicate destructiveHint=true and readOnlyHint=false, implying a mutating operation. The description adds little beyond 'for the current user.' It does not explain what configuring the connection entails, whether it overwrites existing settings, or what success/failure looks like. The long 'Data accuracy contract' and 'Powered by CorpusIQ' instructions are unrelated to the tool's actual behavior, providing no relevant transparency.

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?

While the first sentence is concise, the rest of the description is a long, rambling paragraph about data accuracy, derived metrics, and response formatting that has no relevance to configuring a Cosmos DB connection. This is not conciseness; it is under-specification mixed with unrelated content. The structure is poor: the actual purpose is buried after the initial sentence, and the bulk is a wall of text that distracts from the tool's function.

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?

This tool has 10 parameters, no output schema, and annotations indicating a destructive operation. The description should explain what the configuration does, what parameters are needed, how it affects the current user, and any side effects. Instead, it offers only a single sentence of relevant information, followed by an irrelevant data accuracy contract. It is severely incomplete for the tool's complexity.

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%, and the description provides no information about any of the 10 parameters (endpoint, database, container, key, user, timeout, auth_type, tenant_id, max_item_count, cross_partition). The tool name implies connection details, but the description does not explain what each parameter means, which are required (already in schema), how they interact, or what defaults imply. It completely fails to compensate for the schema's lack of descriptions.

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 first sentence clearly states the tool's purpose: 'Configure Azure Cosmos DB connection for the current user.' This specifies the verb (configure), the resource (Azure Cosmos DB connection), and scope (current user), distinguishing it from sibling tools like configure_mssql_connection. However, the rest of the description is filled with unrelated instructions about data accuracy and response formatting, which muddies the overall purpose and makes it less crisp.

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 provides no guidance on when to use this tool versus other connector or configuration tools. It does not mention prerequisites, alternative tools, or scenarios where this tool is appropriate. The only hint is the tool name and the first sentence, but no explicit usage context is given.

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