discover_dkim

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

Annotations already include readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=true. The description adds context beyond these: it explains the heuristic behavior (50 queries), the inconclusive miss result due to no enumeration protocol, and that no auth is needed. It doesn't describe the exact return format, but given the strong annotation coverage, the additional behavioral details are sufficient. No contradiction with 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?

The description is dense but well-structured: it opens with the core purpose, then explains the two modes, lists return components, and ends with usage guidance and a safety note. Each sentence adds value, with no filler. It uses bullets and clear active verbs, making it scannable for an agent.

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's moderate complexity (two modes, a caveat about inconclusive results), the description is nearly complete. It covers purpose, behavior, parameters, and safety. The only minor gap is that it doesn't specify the exact structure of the returned 'parsed key tags' or 'public-key strength', but since there's no output schema, this could be helpful. Still, the description is sufficiently complete for an agent to decide and invoke correctly.

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?

The input schema has 100% coverage: it describes `domain` as 'Domain name only' and `selector` as 'Optional exact DKIM selector.' The description adds meaningful context about selector usage, including examples (selector1 or google) and the distinction between exact and heuristic modes. This adds value by explaining the consequences of omitting the selector, which the schema alone doesn't convey.

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 what the tool does: 'Read-only DKIM check for a domain'. It distinguishes two modes: heuristic with 50 common selectors and exact lookup with a specific selector. This uniquely separates it from sibling tools like check_dmarc or check_spf, as it explicitly mentions DKIM and the selector-based functionality.

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 explicitly provides when-to-use guidance: 'Use exact mode whenever the selector is known; use check_email_security for the broader SPF/DKIM/DMARC overview.' It also notes the inconclusiveness of the heuristic miss, which is valuable context for the agent deciding when to rely on results. This directly addresses alternatives among siblings.

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