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

Goes well beyond the annotations (readOnlyHint=false, openWorldHint=true) by disclosing that processing happens in the background, that the business brief is rebuilt and published automatically, that shared content becomes public, and that a sign-in as owner is required. These are consequences an agent could not infer from the structured fields alone.

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?

Front-loads the authorization and core action, but the body is a single long run-on sentence with nested parentheticals covering the file path, which makes it harder to scan than it needs to be. Every piece of information is relevant, yet the packaging costs readability.

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 7-parameter, open-world mutation with no output schema, it covers prerequisites, size limits, visibility, and asynchronous processing. It does not say what the call returns or how the owner can check whether ingestion succeeded or whether a source cap was hit, which leaves a small operational gap.

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?

With only 57% schema coverage, the description compensates well: it defines file_url as a public https link with a 10 MB cap, explains the REST variant (raw body plus Content-Type, file_name in the query), and clarifies that a home-page url pulls the whole site while other listing pages are read standalone. The title parameter is still left entirely to the schema, and the exactly-one-of rule is asserted without explaining what happens if violated.

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 concrete verb and resource ('Add one source the business's AI receptionist learns from') and enumerates the three source modes (file, link, note), so the agent knows exactly what the tool does and how it differs from editing or querying the receptionist.

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 explicit selection rules — 'Pass exactly one of note, url, file_url or file_base64' — plus the owner-only sign-in prerequisite and a caution about private content. It stops short of naming when to use this rather than a sibling like edit_receptionist_source, which is why it is not a 5.

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