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

Adds substantial behavior beyond the annotations: deterministic re-mapping, no model call, "nothing is stored", and a concrete 403 failure mode for unclaimed sandbox workspaces. One tension is worth noting: "nothing is stored" reads as a side-effect-free operation while readOnlyHint=false and idempotentHint=false declare otherwise; this is a soft mismatch rather than a direct contradiction, since the adapter is returned rather than persisted.

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 action and its effect, then prerequisites, in five tight clauses with no filler. Slightly dense comma-splicing keeps it from a 5, but every sentence carries information an agent needs before calling.

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 single-parameter tool with no output schema, it covers what is produced ("Returns the adapter"), that nothing is persisted, and both auth gates that cause failures. The shape of the returned adapter is left unstated, but that is a minor gap given 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?

The schema already documents `plan` at 100% coverage (including nested mapping fields), so the baseline is 3. The description adds real value by specifying the provenance contract — the plan must come from plan_rosetta_mapping — which the schema only hints at.

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 ("Freeze a mapping plan into a pinned adapter") and immediately explains the effect: mappings stamped frozen, deterministic output, no model call. This clearly separates it from plan_rosetta_mapping and translate_with_rosetta in the sibling list.

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?

"Pass plan from plan_rosetta_mapping" names the upstream tool and the exact input source, and the credential/workspace prerequisites tell the agent when the call will be refused. It stops short of saying when NOT to freeze (e.g. versus persisting elsewhere), so it is clear context without explicit exclusions.

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