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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds the citation obligation ('Preserve source and version when citing'), which is real context beyond structured data, but says nothing about out-of-range part handling or what is returned.

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, front-loaded sentences with zero filler: what it reads, how to get the full body, and the citation rule. Every sentence earns its place.

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?

With annotations covering safety and 100% schema coverage, most of the burden is lifted. However, there is no output schema, and the description never says what a 'part' returns (raw text, metadata, numbering) or how it relates to get_legislation, leaving a real gap for a retrieval tool.

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 both 'id' and 'part' are already documented with format and range constraints. The description's reference to 'numbered part' and 'the document's parts value' merely echoes the schema, adding no new syntax or format meaning.

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 and resource: 'Read one law text part.' Combined with the name get_legislation_part, the scope (single numbered part vs. whole document) is clear. It does not, however, explicitly distinguish itself from the sibling get_legislation, so an agent must infer the boundary.

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?

'Read every numbered part for the complete body' implies the tool must be called iteratively to assemble a full document, which is genuinely useful implied guidance. But it never names an alternative (e.g. get_legislation for the whole document) or states a condition under which this tool should not be used.

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