human_stop

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

Adds real context beyond the annotations: it discloses that the stop is blocking ('wait until no future injections are possible') and states the boundary that it does not return the cursor or release user-owned input. That complements destructiveHint/idempotentHint rather than repeating them.

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?

Two sentences, both load-bearing, with the core action front-loaded and the non-effects stated second. No 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?

For a destructive, blocking control tool with no output schema, the description covers the main semantics but leaves open how long it waits, what happens if input is already stopped, and what the caller gets back on success or timeout. The undocumented reason parameter is a further gap.

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% and the single parameter (reason, 1-512 chars) is never mentioned. The description offers no hint about what the reason is for, whether it is recorded, or whether it affects behavior.

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 (cancel) and resource (current or pending input) plus the blocking invariant that follows. An agent can distinguish it from observation/status siblings, though it never names human_pause or human_resume, which are the nearest alternatives.

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 implies when this is appropriate (a hard stop before no further injections can occur) but gives no explicit when-to-use/when-not guidance and does not contrast it with human_pause/human_resume, which an agent would plausibly confuse it with.

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