droid_cancel

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

With no annotations, the description carries the full burden: it discloses the destructive-ish nature of cancel/close and the ownership constraint on sessions. It does not say what happens if no turn is running, whether close is idempotent, or what the caller receives, leaving meaningful behavioral gaps.

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?

A single sentence that front-loads the primary operation and immediately qualifies the two modes. No filler, no restatement of the tool name.

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 two-parameter tool this covers both parameters and both operating modes adequately. Without annotations or an output schema, though, it should say more about outcomes and failure states (e.g., canceling when nothing is running) to be fully self-sufficient.

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 0%, so the description must compensate, and it does: it explains what the 'scope' enum values mean and implicitly defines 'session' as a server-started session identifier. It falls short of stating the expected identifier format or what a session string refers to in other tools.

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 uses specific verbs tied to two distinct resources: canceling a session's running turn versus closing a session. It clearly separates the two modes it supports, though it does not name which sibling tool to prefer when a session needs starting or messaging instead.

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 maps each scope value to its intended operation, telling the agent when to pick 'turn' (there is an in-flight turn to abort) versus 'session' (tear down a session this server started). The constraint that only server-started sessions can be closed is a useful usage guardrail, but there are no explicit exclusions or alternative-tool routing.

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