ddb_interact

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

The description adds rich behavioral context beyond the annotations. It discloses that click/fill require confirm flags as 'safety gates to prevent prompt injection', and gives concrete examples of potential unintended state changes ('deleting a character, leaving a campaign, posting to a forum'). It also specifies that screenshots are unguarded and read-only. No contradiction with the annotations; the destructiveHint=true is aligned with the warning about state changes.

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—two sentences—yet covers the core actions, safety gates, and selector best practices. The first sentence front-loads the purpose; the second sentence explains the critical safety nuance without fluff. Every word earns its place.

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 tool has no output schema, the description adequately covers the main behaviors: actions, confirmation requirements, and selector guidance. The only gap is that it doesn't mention what the tool returns (e.g., screenshot path, success/error messages), which could be useful for the agent. However, for selection and invocation, the description is sufficiently 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?

While the schema already describes all 5 parameters, the description adds important semantic value. It explains the purpose of confirm_click/confirm_fill as safety gates, and provides detailed selector guidance: 'Prefer specific selectors... Hardcoded DnD Beyond class names are unreliable (CSS module hashes change).' This goes well beyond the schema descriptions, helping the agent choose correct selectors.

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 clearly states the tool's function: 'Interact with the currently loaded D&D Beyond page by clicking, filling a form field, or taking a screenshot.' This is a specific verb+resource+scope. It distinguishes itself from sibling tools, which are mostly read-only data retrieval tools, by being the only one that performs live page interactions.

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 provides clear usage context: actions are for the 'currently loaded' page, implying a prior navigation step. It explains the safety gates for click/fill actions and that screenshots are unguarded/read-only. While it doesn't explicitly name alternatives or say 'when not to use', the 'currently loaded page' phrasing and the safety instructions give substantial guidance. A minor gap is the lack of explicit distinction from sibling page-reading tools like ddb_get_page.

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