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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description's extra value is the 5-minute cache TTL and the fact that it returns each tool's read-only hint — both materially useful for deciding how fresh the data is and whether a discovered tool is safe. It stops short of covering failure modes (unknown alias, unreachable instance), which is why it is a 4 rather than 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?

One sentence, front-loaded with the WHEN trigger, followed by scope, payload, and cache note in that order. Nothing is repeated or wasted.

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?

For a one-parameter discovery tool with no output schema, the description supplies what the schema and annotations cannot: the return payload shape, the cache duration, and the exact position in the erp_list_instances → erp_list_tools → erp_call workflow. An agent has everything needed to call 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?

Schema coverage is 100% and the single 'instance' property already documents itself with an example alias. The description only reinforces that exactly one instance per call is expected and that the alias comes from erp_list_instances — a small but non-zero addition, so the baseline 3 applies.

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 ('discover which tools the ERP MCP server of ONE instance exposes') and enumerates the returned payload (name, description, input schema, read-only hint). It is clearly distinguished from erp_list_instances (which instances exist) and erp_call (invoking a tool).

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?

An explicit WHEN clause anchors it in a call sequence: after erp_list_instances, before erp_call. The 'ONE instance' constraint also implicitly rules out trying to enumerate multiple instances in a single call.

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