cursor_reply

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

With no annotations, the description carries the burden and discloses meaningful behavior: same job id and thread preserved, the state transition (input-required -> working -> completed), and a cancel prerequisite. It does not say whether the child follow-up inherits permissions or what the response looks like, but the core behavioral model is well conveyed.

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?

Dense and front-loaded: the primary verb+resource leads, then the two behavioral branches, then the cancel caveat. Nearly every clause earns its place, with only mild repetition.

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?

No output schema exists, so returns are less critical, and the behavioral logic is covered. But with 4 uncovered parameters/enum values and no annotations, the definition leaves the agent guessing on parameter semantics and the meaning of tier — a real gap for a 3-param tool.

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, but it says nothing about jobId, prompt, or the tier enum (consult/plan/execute). 'input' and 'job id' are mentioned only in passing, leaving all three parameters undocumented.

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 ('Send input to a job') and then differentiates two distinct behaviors: resuming a paused task vs. spawning a child follow-up job. This is clear and specific, though it never names a sibling tool directly.

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?

Explicitly states the condition that selects the resume path ('paused in the A2A input-required state') versus the child-job path, and adds a precondition ('Cancel a running job before replying'). Lacks an explicit tie to cursor_cancel by name, but the guidance is actionable.

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