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

Annotations already declare the mutation/open-world/non-idempotent profile, and the description adds substantial context on top: it runs as a job, waits ~50 s then hands back a jobid, revisions often take minutes, and critically that Google produces a NEW artifact with its own id while the original stays. This async-job and non-destructive-output detail is exactly the value annotations cannot convey.

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?

Four dense sentences, each earning its place: core action, artifact-creation semantics, wait/return behavior, and sibling routing plus endpoint. The primary action is front-loaded with zero filler.

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 output schema, the description fully carries the return contract (jobid for polling, job record names the new artifact id) and explains timing expectations. Nothing an agent needs in order to call and follow up correctly is missing.

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%, so the baseline is 3. The description reinforces that the change is driven 'from a prompt' and that the job result names the new artifact id, but adds no syntax or format detail for slide/artifact/replyRef beyond what the schema already documents.

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: 'Change one slide of a completed slide deck from a prompt.' It distinguishes itself from siblings by routing to notebook_get_slide to inspect the slide and notebook_get_job for the async result, so an agent can tell it apart without opening the schema.

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?

Provides clear next-step routing (use notebook_get_job with wait:true, or notebook_get_slide to view). Implies the deck must be 'completed' and that revisions are slow, but does not explicitly state when NOT to use this versus a full regeneration or other artifact tools.

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