mailkite_upload_attachment

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

Annotations only indicate non-read-only/non-idempotent/non-destructive, but the description adds substantial behavioral context: the uploaded file is re-hosted, the URL is time-limited, retentionDays controls its lifetime, and an API key (mk_live_…) is required. It also clarifies transport-specific behavior (raw bytes vs base64). No contradiction with 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?

Five sentences, each earning its place: outcome, usage, input methods, retention, and auth. The most important information is front-loaded, and the dense parentheticals add needed detail without fluff.

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?

For an upload action with no output schema and no required parameters, the description gives the agent everything needed: how to supply the file (one of four ways), what is returned (a URL), how to use the return value, how long it lasts, and what credentials are required. The 'ONE of four ways' guidance prevents invalid calls with zero parameters.

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 100%, but the description adds the crucial 'ONE of four ways' mutual-exclusivity constraint that the schema cannot express, plus the raw-HTTP body alternative that has no JSON parameter. It also clarifies retentionDays defaults and the returned URL's format for send().

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 specific verb and resource: 'Upload a file to MailKite storage and get back a secure, time-limited URL.' It also explains the returned URL's role in send() and contrasts with base64-inlining, making it distinct from sending tools like mailkite_send.

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?

It explicitly frames the tool as the preferred path over 'base64-inlining large files on every send', and gives concrete usage: reference the URL in send() or inline in HTML. It also details when each of the four file-input methods applies (local path for CLI/SDK/local MCP, remote URL for fetch-and-re-host, content as fallback, raw POST body over HTTP).

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