proof

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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, so the description only needs to add context — and it does: it declares the result is deterministic and that the exit code is the verdict, which tells the agent how to interpret the outcome. It stops short of explaining what the returned scope object looks like or how `--verify` interacts with this MCP surface.

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 core purpose and with zero filler. The vocabulary is dense but each sentence carries a distinct fact (what it computes, where verification runs, how to read the result).

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, so the description must convey return content — and it does via 'change class, planned gates and tools' plus the exit-code verdict. Minor gap: it doesn't clarify how an MCP caller (as opposed to a CLI user) observes that verdict or the scope payload.

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 all three parameters (`path`, `task`, `change`) are already documented in the schema. The description reinforces the 'one file' scope of `path` and the notion of change class, but adds no format or constraint detail beyond the schema, so the baseline of 3 applies.

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 names a specific capability: computing the deterministic scope of a change to one file, returning its change class plus planned gates and tools. That is concrete enough for an agent to know what it gets back. It does not, however, distinguish itself from siblings such as `gate`, `route`, or `steps`, which sound like adjacent planning/verification tools.

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 clause 'Measured verification (`--verify`) runs gates and stays on the CLI' implies this tool scopes/plans while actual gate execution happens elsewhere, which is useful routing information. But it never says explicitly when to call `proof` versus `gate` or `route`, and gives no prerequisites or exclusion conditions.

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