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

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=false, so the safety profile is covered. The description adds real value beyond that: "Free" discloses there is no credit cost, and "never moves" discloses immutability of the resulting baseline. It omits other behavior an agent would want — what happens on a duplicate name, whether the baseline can later be deleted, and the fact that repeated calls create distinct baselines given idempotentHint=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?

Two short sentences with no filler and the core immutability guarantee placed early. The leading "Free." is a slightly odd opener but is a useful, terse cost signal rather than waste.

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 four-parameter mutation with no output schema and low schema coverage, the description is thin: it never explains what a baseline is used for downstream, what ref means, or what the caller gets back. An agent can guess the intent but lacks enough to call it confidently alongside mbe_commit and mbe_diff.

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 description coverage is only 25%, with just model_id documented, so the description carries real burden here. It implies the "name" parameter is the baseline label and hints that a specific "version" (the ref, defaulting to main) is being pinned, but it says nothing about message or about valid ref values, leaving two of four parameters unexplained in both schema and prose.

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?

"Name a version of the model as a baseline that never moves" conveys a specific action (mark/name a version) on a specific resource (a baseline) and adds the defining property of immutability. It does not, however, differentiate itself from siblings such as mbe_commit or mbe_export, which an agent could reasonably confuse with versioning operations.

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?

There is no when-to-use guidance, no prerequisites, and no named alternative. The only usage-adjacent signal is the word "Free," which tells the agent about cost but not about when to create a baseline versus committing or exporting.

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