agentglass

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

No annotations are provided, so the description carries the behavioral disclosure burden. It does well by explaining what is scanned, what the output contains (risk level, verdict, evidence), and how the agent should respond. Since scanning a public URL is naturally non-mutating and does not require credentials, the lack of explicit read-only/auth notes is a minor gap rather than a serious one.

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 compact and front-loaded, opening with the core action and resource before explaining the detection scope and return value. Every sentence adds useful information, and the final clause about deciding whether to continue or pause gives actionable context without padding.

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 there is no output schema, the description wisely explains the return format: risk level, verdict, and evidence. It also explains the significance of the result for the agent's workflow. It does not cover failure modes or non-public URL behavior, but for a focused scan tool these are secondary and the core calling context is 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?

Schema description coverage is 100%, so the schema already documents both parameters. The description adds a little context by calling the URL public and linking it to job pages, but it does not add meaning beyond the schema for timeoutMs. This matches the baseline of 3 for high schema coverage.

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 verb and resource: scan a public URL, typically a job posting or application page. It further specifies what is being detected (hidden text, HTML comments, metadata, script content for prompt injection), which makes the tool's purpose immediately clear even without sibling tools to distinguish it from.

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 clearly conveys when the tool is appropriate: when an agent encounters a URL, especially a job posting, and needs to check it for hidden AI instructions before proceeding. It also connects the output to a decision (continue or pause for human review). However, it does not explicitly state when not to use the tool or mention alternatives, so it stops short of full guidance.

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