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

Annotations only cover the safety profile (readOnlyHint=false, openWorldHint=true, idempotentHint=false). The description adds the genuinely non-obvious behavioral facts: this is an asynchronous job, it times out at roughly 50 seconds and returns a jobid to poll, and nothing lands in the notebook until a separate import call. That is exactly the context an agent needs and cannot get from the annotations.

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-loaded with the purpose and dense with distinct facts; every clause carries information. The semicolon-heavy, telegraphic packing ('A job: waits up to ~50 s, then returns the jobid') trades a little readability for compactness, keeping it just short of ideal.

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?

There is no output schema, so the description correctly supplies the return contract (a jobid after up to ~50 s) and the polling path via notebook_get_job. Combined with the import prerequisite, an agent has everything needed to invoke and follow through correctly.

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 coverage is 100%, so the schema already defines the four optional/required parameters, and baseline would be 3. The description earns above baseline by attaching operational meaning to the enum values — Discover timing, the deep-mode written report, and the drive-only-works-with-fast constraint, the latter of which appears nowhere in the schema.

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 ('find new sources for a notebook') and immediately qualifies it with the two modes and two source types. It also names the follow-up siblings (notebook_get_job, notebook_import_research), so an agent can place it precisely in the workflow without reading other schemas.

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 criteria for both enums ('fast ... usually under a minute' vs 'deep ... a few minutes', 'web or drive ... fast only') and names the follow-up tools. It stops short of stating when NOT to use this tool versus alternatives like notebook_add_sources or notebook_search_sources, so it falls just below the top mark.

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