CDP MCP Server

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

With no annotations provided, the description carries full burden and adds valuable behavioral context: it specifies the HTTP method (POST), endpoint pattern (/v2/{tenantId}/spam/score), required request format (JSON array), and error behavior for incorrect input. However, it doesn't mention rate limits, authentication needs, or what the scoring output looks like (though output schema exists).

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 appropriately sized and front-loaded with the core purpose. Every sentence adds value: first states purpose, second specifies request format, third warns about error. No wasted words, though the parameter mismatch slightly reduces effectiveness.

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 2 parameters with 0% schema coverage, no annotations, but an output schema exists, the description is moderately complete. It covers the endpoint and format requirements but fails to properly document parameters (creating confusion with mismatched names). The output schema reduces need to describe return values, but parameter documentation gap is significant.

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 compensate but doesn't adequately explain parameters. It mentions array elements like 'subject', 'body', 'fromAddress', 'fromName' which don't match the actual schema parameters ('body' and 'tenant_id'). This creates confusion rather than adding clarity beyond the bare schema.

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: 'Score email/message content for spam likelihood' with specific verb ('score') and resource ('email/message content'). It distinguishes from siblings by its unique spam scoring function, though it doesn't explicitly contrast with similar tools since none exist in the sibling list for spam analysis.

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 implies usage context by specifying the required JSON array format and error condition ('Passing a single object returns E400'), but it doesn't provide explicit guidance on when to use this tool versus alternatives or any prerequisites. No sibling tools offer similar spam scoring, so differentiation isn't needed.

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