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

Description claims 'takes no parameters' but input schema requires a 'rationale' parameter. This is a factual contradiction. The read-only claim matches annotations but the parameter misstatement misleads. No contradiction with annotations, but schema contradiction reduces transparency.

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?

Two sentences are front-loaded, but the inaccurate claim about parameters undermines conciseness. A correct description would be similarly brief but accurate. The error makes it not 'appropriately sized'.

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 simple tool, description covers purpose and usage but fails to acknowledge the required 'rationale' parameter. Without output schema, description should at least hint at return values or the need for rationale. Missing key context.

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?

Despite 100% schema coverage, description incorrectly states 'takes no parameters' and completely ignores the 'rationale' parameter. This actively misleads the agent, providing no useful semantics and instead giving false information.

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?

Description clearly states 'Get the CoinPaprika MCP server's status and configuration' with specific attributes (uptime, mode, enabled features). It distinguishes from sibling tool getGlobal by noting market health vs server status.

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?

Explicitly provides usage examples ('is the server up', 'what mode am I in', 'server status') and tells when not to use (for market health, use getGlobal). Clearly defines the tool's use case.

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