node_inspect

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

Annotations already declare readOnlyHint=true and destructiveHint=false, safely identifying this as a read operation. The description adds behavioral context by stating the swarm manager requirement and summarizing the returned fields (role, availability, status, manager reachability), exceeding the annotation bar without contradiction.

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 concise, using three sentences for purpose/context plus a clean args/returns block. Every sentence contributes unique value—no filler or repetition.

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, read-only inspection tool, the description is fully complete: it states the purpose, usage preconditions, alternative tools, parameter meaning, and return structure. The absence of an output schema is mitigated by the explicit return summary.

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?

The schema provides only a parameter name with no description, so the description carries the burden. It defines id_or_name as 'The node id or hostname (as shown by node_list)', which gives the agent the necessary context for providing a valid value.

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 opens with 'Get a swarm node's full inspect payload by id or name', a specific verb and resource that clearly defines the operation. It distinguishes this from sibling tools like node_list (enumeration) and node_update (modification).

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 explicitly recommends using node_list to enumerate nodes first, mentions docker://nodes for a fleet summary, and contrasts with service_ps for service-to-node mapping. It also notes the prerequisite that it must run against a swarm manager.

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