Read a tax regulation

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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, so the description needn't cover safety. It adds genuinely useful behavior beyond annotations: the ~6000-character part size, the parts>1 pagination protocol, and the ability to scope to one article. Return shape (title, kind, number, dates, issuer, PDF link, reading order) is also disclosed.

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 core verb+resource sentence, then source, then pagination and article guidance. Three sentences, no filler. Slightly dense but every clause carries actionable information.

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 no output schema, the description compensates by naming the returned fields (title, kind, number, dates, issuer, PDF link, text in reading order) and covering pagination and article scoping. An agent has everything needed to call and re-call it correctly.

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 goes beyond the schema by explaining the pagination semantics of `part` (parts count, 6000-char chunks, call again) and the intent of `article` as an alternative to reading an entire ~300-article law, adding practical meaning to both optional parameters.

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 ('Return the full text of one tax law, circular, ruling or opinion, or just one article of it') and implicitly distinguishes itself from the sibling search tool by being a read-one-document operation. The scope (whole document vs single article) is spelled out, so an agent can tell it apart from tx_regulations_search.

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 explicit operational context: source site, the fact that long laws are paginated ('parts > 1 means call again with part=2, 3, ...'), and when to use `article` for large laws. It does not state when NOT to use the tool or name a direct alternative by name (the id dependency on tx_regulations_search appears in the schema, not the description), which keeps it short of a 5.

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