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

Goes well beyond the readOnlyHint/openWorldHint annotations by disclosing the verdict vocabulary (healthy | degraded | down | unknown), the metrics returned, and that pricing/payment info is included. This is exactly the kind of contextual detail annotations don't carry.

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?

Dense but front-loaded with the WHEN TO CALL trigger before the return-value inventory, so an agent sees the usage condition first. The single long sentence is packed but every clause carries information; slight trimming of the return list could improve it.

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?

With no output schema, the description fully compensates by enumerating the returned fields (verdict, success rate, p50/p95, error signatures, breakage, endpoint, pricing), and the single input's accepted formats are covered in the schema and reinforced in prose.

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 already 100%, but the description adds real meaning: the exact Glimind id is not required and the response reports what the input resolved to. That resolution behavior is not captured by the schema alone, justifying above the baseline 3.

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 (check reliability) plus resource (an MCP tool/server), and enumerates exactly what it returns: verdict, success rate, latency, error signatures, breakage, endpoint, pricing. An agent can distinguish it from siblings like verify_tools or audit_server because the description frames it as a live reliability lookup rather than a test or audit.

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 states when to call: before invoking an unfamiliar/external tool and after any failure, timeout, or 4xx/5xx, with the reason (is it down for everyone or local). It does not name sibling alternatives such as preflight_tools or verify_tools, so it stops short of a 5.

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