Update SSH Connection

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

Discloses substantial behavior beyond the annotations: the existence precondition, non-destructive partial-update semantics, the explicit exclusion of secret rotation, and the exact response shape ('only connectionId, workspaceId and source'). This is fully consistent with annotations (readOnlyHint=false, destructiveHint=false) — there is no 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?

Four sentences, each carrying distinct information: purpose, precondition, update semantics, and capability/result boundary. Every sentence earns its place and the purpose is front-loaded. Slightly dense with unexplained terms ('CommandBus,' 'source') but appropriately sized.

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?

Covers purpose, precondition, partial-update behavior, a capability exclusion, and result shape — substantial for a partial-update tool with an output schema. Gaps are the absence of routing guidance to siblings (create_connection, db.update_connection) and no clarification of what 'selected workspace' means or how it maps to the optional workspaceId parameter.

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?

With 0% schema description coverage, the description adds one cross-cutting semantic — 'omitted fields and stored credentials are preserved' — which is the most important behavior for these optional parameters. It does not explain individual fields such as authKind, keyPath, or how they interact, leaving the schema's bare types and enum to carry that weight. A 3 reflects partial compensation for a large coverage gap.

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: 'Updates saved connection metadata.' This clearly differentiates it from sibling create/delete/test connection operations by name and description. The phrase 'through CommandBus' is unexplained jargon that adds little for an agent, and it does not explicitly contrast with unfour.db.update_connection, so a 4 rather than 5.

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?

Gives concrete usage context: the precondition that the ID 'must exist in the selected workspace,' the partial-update guarantee that 'omitted fields and stored credentials are preserved,' and the capability boundary that 'secret rotation is not exposed.' These explain when and how the tool should be invoked, though no alternative sibling tool is named for cases like secret rotation or new connections.

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