attested_run

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

With no annotations, the description carries the full burden and does so well: it discloses that the command executes in a shell with the caller's permissions, that this is effectively shell access requiring per-call approval rather than blanket approval, and that it writes a receipt file. It also describes the return payload (receipt summary; failure packet with failing tests, messages/stacks, console errors, failed requests, evidence paths, rerun command) and adds a prompt-injection warning that packet contents are data, not instructions.

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?

Front-loaded with the core value proposition, then prerequisites, execution safety, and output contents in a logical order. Dense but nearly every sentence adds information. Minor redundancy between 'write a test receipt' and 'Returns the receipt summary' and the slightly awkward parenthetical path.

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?

There is no output schema and no annotations, yet the description explains return values, failure-mode payloads, approval/permission needs, and the required workflow (rerun until PASSED). For a shell-executing test runner this covers what an agent needs to invoke it responsibly; only timeout and concurrency behavior are unaddressed, which are minor.

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 100%, so each of the five parameters is already documented in the schema, including the CTRF report requirement and the /healthz pre-check for target_url. The description adds general context (shell execution, receipt output) but no parameter-level meaning beyond that; baseline 3 is appropriate.

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 and resource: run a test command through `attested run` and write a test receipt at attested/receipt.json. The framing 'Use instead of screenshots to show that a change works' makes the intent concrete. It never names the siblings (attested_status, attested_packet), and since it also says it returns the failure packet on failure, an agent may not immediately see why attested_packet exists separately.

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?

Gives clear usage context: run before opening a PR, fix and rerun until result is PASSED, and use instead of screenshots. That is a strong trigger condition plus an alternative it replaces. It stops short of explicit exclusions or naming the sibling tools for follow-up (status/packet retrieval), so routing among siblings is only implied.

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