Datadog MCP Server

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

No annotations are provided, so the description carries the full burden. It discloses behavioral traits: the data availability timing (current month, around 12th), access restrictions (parent-level organizations only), and includes HTTP response codes (200, 400, 403, 429) with examples. However, it lacks details on rate limits beyond the 429 error mention, authentication needs, or whether this is a read-only operation (implied by 'Get' but not explicit). The description adds useful context but doesn't fully cover all behavioral aspects for a tool with no annotations.

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 front-loaded with purpose and usage guidelines, but it includes redundant parameter details that are already in the schema and extensive HTTP response examples that could be condensed. The structure is logical but verbose, with some sentences (like the parameter descriptions) not earning their place as they duplicate schema content. It's appropriately sized for a tool with no annotations, but could be more concise.

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?

Given the tool's moderate complexity (2 parameters, no annotations, but with output schema indicated by context signals), the description is fairly complete. It covers purpose, usage constraints, parameters (though redundant), and behavioral aspects like responses. The output schema exists (per context signals), so the description doesn't need to explain return values in detail. However, it could better address sibling differentiation and authentication details to be fully comprehensive.

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 input schema has 100% description coverage, with both parameters ('view' and 'include_connected_accounts') fully documented in the schema. The description repeats this parameter information verbatim in the 'Query Parameters' section, adding no new meaning beyond what the schema provides. According to the rules, with high schema coverage (>80%), the baseline is 3 even with no additional param info in the description.

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 clearly states the tool's purpose: 'Get projected cost across multi-org and single root-org accounts.' It specifies the verb ('Get') and resource ('projected cost') with scope ('multi-org and single root-org accounts'). However, it doesn't explicitly differentiate from sibling tools like 'GetCostByOrg' or 'GetEstimatedCostByOrg' beyond mentioning it's for 'projected' costs, which is somewhat implied but not strongly contrasted.

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 clear context on when to use this tool: 'Projected cost data is only available for the current month and becomes available around the 12th of the month' and 'This endpoint is only accessible for parent-level organizations.' This gives temporal and access constraints. However, it doesn't explicitly state when not to use it or name alternatives among siblings, such as 'GetEstimatedCostByOrg' for non-projected costs.

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