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

Goes well beyond the readOnly/openWorld annotations: it discloses subscription gating, chunked delivery of 12,000 characters, the continuation mechanism, and — importantly — that the call consumes the subscription's daily document quota. That quota cost is exactly the kind of side effect an agent needs before calling.

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?

A single dense sentence, front-loaded with the resource and id source, then access conditions, chunking, and budget cost in order of decision importance. Slightly heavy as one sentence but no wasted clauses.

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 return-value burden and does so reasonably (metadata plus conditionally full text). Remaining gaps — behavior without subscription and how to detect the final chunk — are minor but real for a paged 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 coverage is already 100%, but the description adds conceptual meaning the schema lacks: that de_la is a chunk cursor tied to 12,000-character segments rather than an arbitrary offset. It doesn't cover alternative id format risk/validation beyond what the schema example shows.

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 (retrieve) and resource (a BPI publication) and anchors the identifier source to the sibling tool publicatii_bpi, so an agent can tell it apart from the listing tool. It also distinguishes the payload clearly: metadata always, full text conditionally.

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?

Explains that the id comes from publicatii_bpi and that full text requires an active subscription or paid firm access, and describes the continuation pattern via de_la. It does not state what happens when access is absent (metadata-only versus error), which is the main missing guidance.

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