Show a single MagicSword endpoint

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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuinely useful context beyond that: the required scope ('Requires endpoints:read') and the breadth of the payload it touches (OS, architecture, policy, compliance, AMSI, heartbeat, upgrade state). It stops short of describing not-found behavior or payload size.

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, no filler: the retrieval semantics come first and the permission requirement second. Every clause carries information and nothing is repeated.

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 enumerated field list compensates well by telling the agent what data comes back, and the auth scope is disclosed. Minor gaps remain — no error/not-found guidance and no mention of payload richness for very detailed endpoints.

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 parameter already documents itself as an 'Endpoint UUID returned by list_endpoints'. The description only restates 'by UUID', adding no format or provenance detail beyond the schema, 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 ('Fetches one endpoint') and adds the retrieval key ('directly by UUID'), which cleanly separates it from the sibling list_endpoints. An agent can pick this tool without opening its schema.

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?

Usage is implied by 'by UUID' — you reach for this when you already hold an endpoint identifier rather than a filter set. However, it never explicitly names list_endpoints as the alternative path or states when-not-to-use, so the routing is left to inference.

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