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

With no annotations, the description carries full responsibility for behavioral disclosure. It goes beyond a simple summary by revealing the parallel Cloudflare DoH query method, the 5-second timeout per selector, and the exact return structure (CheckResult with ok/error statuses, found/notFound arrays). This is detailed and transparent, leaving little surprise about how the tool operates.

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 (roughly 80 words) yet packs a clear purpose, usage guidance, implementation details, and return format into a single paragraph. It's front-loaded with the operative verb and resource, and every sentence adds unique value without repetition or filler.

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 tool with only two parameters, no output schema, and no annotations, this description is remarkably complete. It explains what the tool does, when to use it, how it executes (parallel DoH, timeout), and exactly what the returned data looks like. The explicit output structure compensates for the missing output schema, and the use cases are clearly specified.

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 already provides 100% coverage for both parameters, describing valid domain formats and the default selector set. The description's mention of supplying or omitting selectors merely echoes the schema's own instructions, adding no new semantic insight beyond what the structured schema already conveys.

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 'Core dossier check' and then specifies exactly what it does: 'Probe a domain's DKIM public keys by querying <selector>._domainkey.<domain> for each selector.' This clearly distinguishes it from sibling tools like dossier_dmarc or dossier_spf, and the verb 'probe' plus resource 'DKIM public keys' is specific and unambiguous.

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?

It provides clear usage context: 'Use to verify signing configuration or discover active selectors.' It also gives practical guidance on when to supply selectors versus omit them to use the built-in set. While it doesn't explicitly name alternative tools for when not to use it, the sibling tool suffix makes the domain-specific scope obvious.

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