List SSH Command History

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

Annotations already declare the tool safe (readOnlyHint=true, destructiveHint=false), and the description adds meaningful behavioral disclosure beyond those flags: sensitive commands 'are excluded or replaced with [redacted command]', results are 'workspace-scoped', and fields are returned 'when recorded'. The redaction behavior and scope guarantees are exactly the kind of non-obvious context agents need and are not inferable from annotations.

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 tight sentences and roughly 90 words cover purpose, return shape, scope guarantees, redaction policy, and the follow-up workflow. The first sentence front-loads the core purpose, and no sentence is wasted on restating annotations or schema text.

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 read-only tool with 6 optional (100% schema-documented) parameters, an output schema, and rich annotations, the description covers the remaining gaps: what fields come back, what is excluded (terminal buffers, session logs), redaction behavior, and the recommended post-step (drafting a task). No material behavioral question is left unaddressed.

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 description coverage is 100%, so the rubric baseline is 3. All six parameters are individually documented with type, constraints (max 200, RFC 3339 format), and edge-case behavior ('Unknown or out-of-workspace connections return an empty list'). The description adds workspace-scoping and redaction context, but no parameter-level semantics that meaningfully exceed what the schema already provides, so a baseline 3 is appropriate.

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 a specific verb+resource+scope: 'Lists structured SSH command history for the current MCP workspace,' and enumerates the returned fields (connection, command, executedAt, cwd/exitCode/durationMs). It clearly differentiates from close siblings like unfour.api.list_history and unfour.activity.list by scoping to SSH commands and explicitly ruling out terminal buffers/session logs.

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?

Explicit when-to-use guidance is present: 'Use this to inspect recent host activity, then draft a reusable SSH Task for the user to confirm,' along with a pointed when-not instruction: 'Do not call unfour.ssh.save_task unless the user explicitly asks to save the draft.' It could be stronger by naming read-alternatives (e.g., when to prefer activity.list), but the primary workflow and one key guardrail are explicit.

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