reload

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

No annotations are provided, so the description carries the full burden. It discloses side effects: tears down stale child connections, drops cached tool schemas, re-enumerates catalog, emits notifications, and notes the caveat about capabilities not being registered if the hub started with no exposed servers. This is rich behavioral context beyond a simple 'reload' statement. It doesn't mention auth requirements or rate limits, but for a reload tool those are less critical.

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?

The description is dense but well-organized: main effect, use cases, parameter behavior, exposed-server behavior, and caveat. It's longer than the typical one-liner but every sentence adds information. The caveat is a bit long but valuable. Slight deduction for the caveat being somewhat verbose and the sentence about non-exposed servers being a bit dense.

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 tool with one optional parameter and no output schema, the description covers the main action, side effects, when to use, parameter semantics, and edge cases. The caveat about exposed servers and host reconnection is exactly the kind of context an agent needs to avoid incorrect assumptions. Nothing critical is missing.

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 `server` is described in the schema. The description adds meaning by explaining the behavioral difference when `server` is set: only that server is reloaded, faster, no config re-read. This goes beyond the schema's 'only reload this server' and gives the agent a decision-relevant semantic.

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 states a specific verb ('reload'), a resource ('mcp-hub'), and enumerates concrete effects: re-reads config files, reconciles the server set, tears down stale child connections, and drops cached tool schemas. It clearly distinguishes itself from siblings like list_servers or get_server_tools by describing the reconciliation and cache-dropping behavior.

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 use: after editing the hub's config, or after a child server's tools have changed. It also gives the alternative path: if `server` is given, only that server is reloaded (faster, no config re-read). It even notes a caveat about exposed servers and host reconnection, which helps an agent decide when reload is appropriate.

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