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

Annotations declare readOnlyHint=false and openWorldHint=true, but the description adds the crucial non-obvious behavior: an outbound measurement is triggered, and for uncatalogued tools it may take ~20 minutes. That latency disclosure is exactly the kind of context annotations cannot carry; only the absence of rate-limit or failure-mode detail keeps it from a 5.

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 plus an example, front-loaded with the core purpose and the return payload. The example earns its place by showing the URL form; minor cost is that it illustrates only one of the two input modes.

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?

No output schema exists, yet the description enumerates the returned fields (verdict, success rate, latency, last 20 checks), which is what an agent needs to decide to call it. Missing only the semantics of 'verdict' values. Adequate for a two-optional-param tool.

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% and both params are documented, so baseline would be 3. The description adds real value by signalling the params are alternatives (catalog id OR MCP URL) and giving a concrete example, clarifying that neither is required.

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?

States a specific verb and resource: measures reliability of ONE known tool identified by catalog id or MCP URL, and enumerates the outputs (verdict, success rate, latency, last 20 checks). The 'ONE known tool' framing separates it from discovery siblings like find_capability, but it never names an alternative directly.

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 establishes the precondition (a known tool, by id or URL) and warns that unknown tools take ~20 min, which is implicit guidance on when it is slow. It does not state when to use this versus find_capability or check_shop, nor any exclusion.

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