Verify source integrity

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

With no annotations, the description carries the load and does well: it discloses the exact file it reads, implies a read-only comparison, names the output flag clean, and prescribes the remedy on failure. Gaps remain around behavior when manifest.json is missing or when files are untracked, which an agent would want to know before interpreting clean=false.

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: the mechanism first, the purpose second, the failure action last. Every sentence earns its place and the safety-critical instruction is not buried.

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 zero-parameter, no-annotation tool with no output schema, the description covers mechanism, intent, and the critical failure path. It stops short of describing the rest of the response shape (which files mismatched, counts), which the agent must discover at call time since no output schema exists.

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?

Zero parameters, so there is no parameter semantics to explain; baseline 4 applies. The description correctly implies full-repo scope with no filtering options, which is the only semantically relevant fact for a no-arg tool.

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+method: SHA-256 verification of tracked source/config files against integrity/manifest.json. That is unmistakably distinct from every sibling (palette, draw, animate, project tools), so an agent can select it without opening a schema.

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?

"Use it to prove no agent edited the code" gives a concrete condition for calling it, and the failure branch is fully specified (stop and ask a human to restore on clean=false). What is missing is the complementary trigger — when in a workflow to run it (before export, after generation) — and any statement about what to do when the manifest is absent.

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