discover

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

Consistent with readOnlyHint=true and openWorldHint=true, and adds real context annotations don't carry: the output is pasteable config, brand_terms suggestions are commented out, and persistence happens only via a separate CLI flag. Auth scope is gestured at ('the key can read') but rate limits and failure modes on unauthorized keys are not described.

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?

Three tight sentences, front-loaded with the resource enumeration and followed by output shape and the read-only caveat. Domain jargon ([[sites]], brand_terms) is justified because those are the literal artifacts produced.

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?

No output schema exists, and the description does cover the return shape well enough to act on. However a 1-param tool whose sole parameter is entirely undocumented leaves the agent guessing about `profile`'s effect on results.

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 0% and the description never mentions the single `profile` parameter, so the agent cannot tell whether it narrows the scan, names the target config file, or both. With only one optional param the damage is limited, but the description does nothing to compensate for the coverage gap.

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?

States a specific verb+resource: enumerates Search Console properties and GA4 web streams, matched by domain, plus the shape of what it emits ([[sites]] blocks). 'For any site not in a profile yet' implicitly contrasts with the profile-oriented sibling `sites`, but no sibling is named explicitly.

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?

Usage is implied rather than stated: you call it to gather config blocks for unprofiled sites. It does clarify the read/write split ('Reads only; the user adds the blocks with `dottide discover --write`'), which tells the agent this tool will not persist anything. No explicit comparison to siblings like `sites` or `traffic`.

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