human_key

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

Annotations already declare destructiveHint=true and non-idempotent, so the safety profile is covered. The description adds genuinely non-structured context: the key must be on an allowlist, Enter may submit (the reason it is destructive), and clipboard operations are out of scope. It omits the most operationally important traits – that the target must be focused/foreground, and how pause_policy/threshold_px alter timing behavior.

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, front-loaded with the constraint, and no filler. The terseness is close to under-specification rather than padding, so it is efficient but leaves little substance behind.

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?

This is a destructive, nested-schema tool with no output schema and no parameter documentation; the description should carry far more of that burden. Critically, an agent cannot learn which keys are on the allowlist, how to obtain a valid hwnd, or what pause_policy governs – all of which are required to invoke it 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 description coverage is 0% across 5 parameters, including a nested pause_policy object with seven unexplained integer fields. The only semantic aid is the word "allowlisted," which implies the key parameter is constrained to a known set the schema does not enumerate; hwnd, modifiers, pause_policy and threshold_px receive no explanation in either place.

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 phrase "One allowlisted editing/navigation chord" identifies the resource (a single key chord from a restricted set) but uses no verb and never mentions the hwnd/target window, so what the tool actually does to the system has to be inferred. It partially differentiates from clipboard siblings (human_copy/human_cut/human_paste) but not at all from human_type or human_input_plan.

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?

"Clipboard actions require dedicated tools" is an explicit when-not-to-use that routes to named siblings, which is real guidance. However there is no positive statement of when to prefer this over human_type/human_input_plan, and no mention of the precondition that the target window must be active or how to get an hwnd.

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