Plan Remediation

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

The description reinforces the annotations (readOnlyHint=true, destructiveHint=false) by reiterating 'read-only snapshot' and 'without executing changes,' and adds the behavioral nuance that remediation guidance requires approval. It does not contradict the annotations and provides context beyond what the structured annotations alone communicate.

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 a single, tightly worded sentence that front-loads the key action and outcome. Every phrase earns its place: 'current read-only snapshot' specifies state and safety, 'approval-required remediation guidance' defines the deliverable, and 'without executing changes' prevents misuse. No wasted words.

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?

Given the presence of an output schema (which covers return values), clear annotations, and the tool's simple parameter structure, the description sufficiently covers the essential context: what the tool does, that it is read-only, and that it produces guidance rather than direct changes. The combination of description, schema, and annotations makes the tool's role and safety profile complete.

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 has only one parameter ('connection') with nested sub-properties, but top-level schema description coverage is 0%. The tool description does not explain that the connection object is required for accessing the target host, nor does it clarify how to supply SSH credentials. The nested schema fields are self-descriptive, but the description fails to bridge the gap between the 'connection' parameter and the tool's purpose.

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 action ('collect a current read-only snapshot') and a clear deliverable ('produce approval-required remediation guidance'), with an explicit constraint ('without executing changes'). It distinguishes itself from sibling tools like 'snapshot' and 'analyze_server' by focusing on remediation planning rather than raw data collection or analysis.

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 phrase 'without executing changes' clearly signals when to use this tool: for planning and guidance, not for actual remediation. It also implies that this is a non-invasive, read-only step. However, it does not explicitly name alternative tools for when changes should actually be executed or when a deeper analysis is needed, so it lacks formal exclusions.

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