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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds behavioral context beyond the annotations by committing to a factual, criteria-based output and explicitly disclaiming subjective winners, which shapes the agent's expectations.

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 with no filler; the main verb and resource appear first and the criteria list is compact. It is appropriately sized for the tool's scope.

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?

The tool has a single parameter, an output schema, and annotations covering side effects. The description covers purpose, scope, comparison dimensions, and stance, so an agent has everything needed to invoke it correctly.

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?

With 100% schema coverage, the refs parameter is already described as 'Slugs or ids to compare'. The description reinforces the min/max by saying 'two to five MCPs', but adds no new semantic detail such as example slug formats or default behavior.

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 names a specific operation ('factual side-by-side comparison') with a clear resource scope ('two to five MCPs') and enumerates the comparison axes. The closing 'No subjective winner is chosen' distinguishes it from recommendation-oriented siblings like find_mcp_for_task and recommend_stack.

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 the tool is for comparing explicit MCPs, but it never states when to prefer it over alternatives or mentions exclusions. An agent must infer that this is not for finding or searching MCPs.

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