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

Goes well beyond the readOnlyHint/closed-world annotations by disclosing the access prerequisite (owners only, needs sign-in), the exact payload the caller receives (sources with extracted text, the business brief, owner instructions), and the fact that the brief is live immediately upon writing. It also adds a real behavioral caveat: source text is untrusted data from owner files and websites that must not be treated as instructions.

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 permission constraint and primary use are front-loaded, and every clause carries information about what is returned. It is dense and slightly run-on, with UI cruft ("Teach your AI, also at https://latchbell.com/app/knowledge") that does not help the agent decide or invoke.

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?

With no parameters, no output schema and safety already covered by annotations, the description supplies what the structured data cannot: the shape of the returned knowledge base and the auth requirement. Only minor gaps remain, such as the response format or size of the source collection.

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 tool takes zero parameters, so there is nothing for the description to disambiguate; the schema already declares an empty object. Baseline for a parameterless tool applies, and the description adds no argument-level meaning because none is possible.

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?

Uses specific verbs ("see", "Show") against a precisely enumerated resource: the AI receptionist's sources, business brief and owner instructions. The clause "before teaching it" implicitly separates this read view from the teaching/update siblings, so an agent knows this is the inspection tool rather than a mutation tool.

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?

Gives a clear triggering context ("Use to see what the business's AI agent knows before teaching it"), which tells the agent to call this prior to editing. It stops short of naming the alternatives (add_receptionist_source, edit_receptionist_source, update_receptionist) as the tools to use instead when the goal is to change something, so the when-not side is only implied.

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