nymrel_surety_guard

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

With no annotations at all, the description carries the full disclosure burden. It discloses what it intercepts (destructive commands, path traversal, unconstrained deletes) and when (before agent execution), but leaves the outcome undisclosed: what happens when a command is flagged — does it return an error, a structured block verdict, or halt execution entirely? There is no output schema to fall back on, so this gap is meaningful for an agent deciding whether it can proceed after invoking this tool.

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?

A single dense sentence front-loaded with the core identity ('Pre-execution safety firewall') followed by enumerated threat categories and the timing ('before agent execution'). There is zero filler and every element earns its place. It is slightly long and could be split into two sentences for readability, but the informational density justifies the length.

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?

The tool is conceptually simple with 3 well-documented parameters and no nested objects, so the description adequately covers purpose and inputs. However, with no output schema, the description omits the critical behavioral outcome — what the agent receives when a command is blocked or passed — which is essential for a safety-critical gate tool. The strict-mode behavior is also only partially defined by the schema.

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%, with each parameter (command, strict, workingDirectory) already documented clearly. The description adds category context (examples of destructive commands, path traversal, unconstrained deletes) that reinforces what the command parameter will be evaluated against, which is a modest enhancement over the schema but does not fundamentally extend parameter meaning. The strict parameter's behavior is left entirely to the schema.

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 names a specific mechanism ('pre-execution safety firewall'), a precise action (intercepting), and enumerates the exact categories it blocks (destructive shell commands with concrete examples like rm -rf, DROP, format; path traversal violations; unconstrained deletes). This is clearly distinguishable from the 14 siblings, none of which are safety-firewall tools — the audit/trust/verify siblings are detection tools while this is a gating tool.

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 implies when to use it — before executing potentially destructive shell commands — and the sibling-tool context (sandstorm, local_forge) suggests execution contexts in which this guard applies. However, there is no explicit statement of when to use vs. not use it, no named alternatives to contrast against, and no indication of when an agent should skip this guard and call an execution tool directly.

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