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

Beyond the annotations (which already declare readOnly/idempotent/openWorld/non-destructive), the description discloses the source ('signed PDF on file at the State Secretariat JDIH'), the extraction boundary ('bounded by the next article heading'), and explicit failure behavior ('if the PDF cannot be read as text, or the article is not found, the response says so explicitly rather than returning an empty string'). This is genuinely useful behavioral context an agent cannot get from annotations or schema.

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-loads what the tool returns and follows with usage examples and error behavior; every clause carries information. The em-dash and embedded caveat make it slightly dense, but there is no filler.

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 carries the return-value burden and does so: it explains the returned text's boundaries and failure signaling. Combined with 100% schema coverage, an agent has everything needed to 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 type/number/year/pasal are already fully documented, including the pasal format ('28D', '"Pasal 1" also accepted'). The description reinforces the pasal concept and shows how parameters combine ('UU 13/2003') but adds no new syntax or format guidance, so the baseline of 3 is correct when the schema does the heavy lifting.

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 ('Text of one PASAL (article) of an Indonesian law or regulation') and explicitly distinguishes itself from the sibling that surfaces the same document ('the same official document idn_regulation_detail links to'). An agent can tell it apart from idn_regulation_detail, idn_statute_detail and idn_search_regulations without opening a schema.

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 three example queries ('what does Pasal 1 of UU 13/2003 say', 'text of Article 27 of the Ketenagakerjaan law', 'read Pasal 28D...') give concrete context for when to reach for this tool, and it positions itself relative to idn_regulation_detail. It stops short of an explicit when-not statement or naming which sibling to use for metadata vs. full text, so it isn't a full 5.

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