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

Annotations already set readOnlyHint=true and openWorldHint=false, but the description adds observable behavior beyond that: the Wraps fee is independent of volume, the AWS pipeline items derive from emails and event types, and the events parameter is accepted but inert. These details are not present in the annotations and help an agent understand side effects and limitations. It does not describe the output structure, but that is not a behavioral trait per se.

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 a single paragraph of moderate length, but every sentence adds value. It front-loads the core purpose, then explains key caveats. It could be slightly tighter (e.g., 'six variables interact' is somewhat vague) but remains efficient and well-structured.

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 has 7 parameters and 4 enums, the description covers the input logic thoroughly. However, there is no output schema, and the description does not specify what the return value looks like (e.g., a breakdown or a single number). While the tool's purpose suggests a cost figure, an agent would benefit from knowing the response format to use the result correctly. This is a notable gap for a tool of this 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 coverage is 100%, so baseline is 3. The description adds non-trivial context: it clarifies that the Wraps fee does not vary with volume (relevant to 'tier' and 'billing'), that the AWS-side lines depend on emails sent and event types (relevant to 'emails' and 'events'), and that the events parameter is accepted for backward compatibility but currently ignored. This elevates understanding beyond the schema's plain 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 description opens with a clear, specific verb and resource: 'Estimate the real monthly cost of running email on Wraps + AWS'. It lists the major components (Wraps fee, SES, EventBridge, etc.) and is distinct from the sibling documentation tools (get_doc, list_docs, search_docs), which serve unrelated goals. An agent can immediately identify this is a cost-estimation tool.

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?

Provides explicit guidance: 'Use this instead of doing the arithmetic — six variables interact'. It warns about the backward-compatible 'events' parameter that does not affect the current estimate, clarifying when to rely on it. While it does not name alternatives, the context and instruction to use this over manual calculation is sufficient.

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