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

With no annotations, the description carries the burden of disclosure. It reveals rate limits (20 calls/day per IP) and authentication requirements (API key for larger files/usage), and hints that files are sent to a server by contrasting with the browser-based alternative where 'files never leave their device.' It does not, however, specify the exact return value or whether the original file is preserved.

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, dense paragraph that front-loads the purpose before covering limits and alternatives. It is slightly long due to the license/API-key instructions, but each sentence carries actionable information, including a URL and fallback option.

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?

Without an output schema or annotations, the description should ideally explain the output format (e.g., returns a new base64 image). It covers usage constraints and rate limits thoroughly but omits the return value and details about how target_size interacts with quality. Given the tool's moderate complexity, this is a notable gap.

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 already documents all six parameters with descriptions, covering 100% of the schema. The description adds a high-level note about 'target size compression and format conversion,' which maps to target_size and format, but does not provide additional syntax or constraints beyond the schema. This meets the baseline for schema-heavy tools.

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 primary function: 'Compress an image (JPEG/PNG/WebP) to reduce file size.' It also notes support for target size compression and format conversion. However, it does not explicitly differentiate this tool from sibling tools like convert_image or optimize_image, relying instead on the verb 'compress' to signal its role.

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 context on when to use the tool (any compression task) and when to seek alternatives: files over 10MB or more than 20 calls/day require an API key, and for browser-based privacy the description suggests compressio.cc. It does not explicitly compare against sibling MCP tools, but the fallback instructions offer practical guidance.

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