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

Beyond the annotations (destructiveHint=false, openWorldHint=false), the description adds real behavioral context: the write is additive and low-risk, no confirmation step is required because it only touches the caller's own record, it is undoable from the same surface, and it returns an ordinary result rather than a plan_token. That is exactly the extra information an agent needs to decide whether to await approval. It stops short of describing rate limits, size limits, or what happens on duplicate saves.

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 purpose and the field list are front-loaded in the first two sentences, and the confirmation paragraph, while long, carries distinct policy information the agent cannot get elsewhere. The CONFIRMATION label could be trimmed slightly, but nothing is genuinely redundant.

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 low-complexity, non-destructive write with no output schema and no nested objects, the description covers purpose, safety profile, and confirmation behavior thoroughly. The remaining gap is the unexplained interaction between 'kind=image' and the text-only payload, which leaves one call path underspecified.

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 0%, so the description must carry the parameter burden and only partly does: it explains that 'payload' is the text to save and that 'kind' is optional with the values text/link/quote/image (repeating the enum already in the schema). It leaves the semantics of 'kind' unexplained — e.g., how an 'image' kind relates to a required non-empty string payload — which is a real ambiguity for a two-parameter tool.

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?

The description states a specific verb and resource — save a snippet to the caller's cross-device clipboard — and names the payload and kind fields, so the agent knows exactly what the tool does. It does not explicitly contrast itself with read-side siblings such as list_clipboard, which keeps it short of a 5.

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?

It clarifies that the tool runs immediately when the caller asks and that destructive, outbound or financial operations are handled differently, which is a useful usage boundary. However, it never tells the agent when to choose this over adjacent capture/write siblings or how to read back what was saved, so routing guidance is only implied.

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