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

Annotations already declare idempotentHint=true and destructiveHint=false, but the description adds genuine context the agent cannot infer: identical replay recovers the original intake, and URL acceptance does not mean the content is ready. Both are non-obvious behavioral traits beyond the structured fields.

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 short sentences, no filler. The core intake behavior comes first and the asynchronous caveat follows where it is needed.

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?

Output schema covers return values and the schema itself fully documents the three parameters, so the description need only carry the async and idempotency nuance, which it does. Minor gap: no indication of authorization or per-agent scoping beyond the agent_id reference.

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 100%, with request_key and content already documented in the schema, so the baseline applies. The description reinforces the client-generated key and the text-or-URL duality but adds no format, length, or validation detail beyond what the schema states.

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 and resource (adds a text or URL source) plus the key-based intake behavior, which separates it from bulk-import siblings like source_import_drive or source_upload. It stops short of naming any sibling explicitly, so the differentiation is inferential rather than stated.

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 gives real operational guidance for URL intake (it is asynchronous; poll source_operation_read; acceptance is not readiness), which tells the agent what to do after calling. It never says when to choose source_add over source_upload, source_import_drive, or source_import_repository, so the selection guidance remains implied.

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