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

With no annotations, the description carries the full burden of explaining behavior, but it only restates the operation name. It does not disclose whether the input is mutated, what the return value looks like, how unknown schema names are handled, or whether normalization involves validation or transformation. The schema name examples hint at targets but not at semantics.

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?

The description is a single 15-word sentence that front-loads the verb and object and includes the most useful differentiators. No redundant or filler language is present, so it is easy for an agent to scan and retain.

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?

The tool lacks an output schema and annotations, so the description alone must cover return values and behavior. It does not state what the normalized output looks like, whether the four schema names are exhaustive, or what happens on invalid input. For a transformation tool operating on nested objects, this is insufficient for an agent to invoke it confidently.

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 input schema documents both parameters with 100% coverage, so the baseline is 3. The description adds meaningful parameter semantics by enumerating concrete target_schema values (invoice, receipt, contact, resume), effectively providing an informal enum that helps an agent pick valid inputs. It does not add anything about the 'data' parameter beyond what the schema states.

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?

The description clearly states the verb ('Normalize') and the resource ('data object') with a concrete target: a named schema. The parenthetical examples (invoice, receipt, contact, resume) sharpen the meaning and suggest a distinction from siblings like extract_table or parse_invoice, though the distinction is not explicitly drawn.

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?

The description offers no guidance on when to use this tool instead of sibling tools such as parse_invoice, structure_text, or validate_structure. There is no mention of prerequisites, input types, or scenarios where normalization is preferable to parsing or validation. The use case is only weakly implied by the schema examples.

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