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

Annotations declare readOnlyHint=false and destructiveHint=false, so the mutation profile is already structured. The description adds real context beyond that: a side effect on generated output ('lifts the rule that kept it out of what Marsell writes') and an auth requirement ('needs an act key') that no annotation covers. Reversibility and whether restoring affects any downstream published state remain unstated.

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 action, so structure is sound. But the vocabulary is idiosyncratic ('What you offer and Sell', 'what Marsell writes') and the trailing 'It needs an act key' dangles without a corresponding parameter, costing more clarity than it buys.

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 two-parameter mutation with no output schema and solid annotations, the description covers action, source-of-truth reference, rejection rule, and side effect. The unexplained 'act key' is the main loose end, and return behavior 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 description coverage is 100%, so the baseline is 3. The description does add the meaningful constraint that effectively one offering is restored per call (matching a name from the removed list), which the schema's minItems:1 alone would not imply. However, 'It needs an act key' references an input that does not exist in the schema, which muddies rather than clarifies parameter expectations.

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 (puts back / restore) and resource (an offering previously removed), and names the two surfaces it affects ('What you offer and Sell' and what Marsell writes). It is clearly the inverse of the sibling offering_remove, and 'offerings_read's removed list' anchors it to the read tool. The odd phrasing ('Marsell writes') is foggy but the action stays identifiable.

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?

Gives an explicit precondition and boundary: only names currently on offerings_read's removed list are accepted, anything else is refused. That routes the agent to offerings_read first and defines the error case. It stops short of naming offering_remove as the opposing operation, so the pairing is inferred rather than spelled out.

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