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

Annotations only declare the write/idempotency profile; the description adds substantial context beyond them: the fork starts from a live disk copy of the source, keeps the same credentials, gets its own address, and the source keeps running without seeing the fork. It also discloses the non-obvious caveats (memory is not copied, processes start fresh as after a power loss, a briq without a volume loses what it wrote) — exactly the surprises that would otherwise break an agent's mental model.

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 decision rule then the mode switch, then behavior, then cleanup — a sensible order. It is dense rather than padded, though the power-cut and disk-replay sentences are long and the volume caveat could be tighter.

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 7-parameter tool with no output schema, the description covers what an agent needs: two operating modes, snapshot semantics, credential and addressing inheritance, process/memory state, disk edge case, and that the return value contains outputs pointing at the fork. Nothing material about the call's consequences is left implicit.

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 the baseline is 3, but the description adds real meaning: the `briq`/`stack` pair is framed as mutually selecting single-vs-whole-stack forking, naming is explained (names kept so the forked app talks to the forked database), and `expose` is conditioned on external access. It does repeat some schema content rather than extend it, keeping it short of a 5.

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 (fork) and resource (a briq or a whole stack), and immediately disambiguates the two modes by naming the parameter that selects each: `briq` for one, `stack` for every briq of a stack. An agent can distinguish this from siblings like briq_up or briq_start without opening the 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?

Explicit when-to-use framing: branch before a migration, a destructive test, or a parallel approach. It also names the exit path and the sibling that implements it ("Keep the fork, or briq_destroy it to throw the attempt away"), which closes the loop on the workflow.

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