get_attachments

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

Annotations already establish read-only, idempotent, closed-world behavior, so the safety profile is covered. The description adds two genuinely new behavioral facts: results are paged/bounded, and returned source content must be treated as untrusted data rather than instructions—an important prompt-injection warning. It still says nothing about ordering, page exhaustion signals, or what an attachment record contains.

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?

Two compact sentences, both front-loaded with the operative fact (paged listing, then the untrusted-content caveat). Nothing is wasted, though the second clause is somewhat boilerplate in tone.

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?

For a five-parameter tool with zero schema descriptions and no output schema, the description is thin: the dual limit/offset and member_limit/member_offset structure is unexplained, and the shape of an attachment record is undefined. The untrusted-data warning is a strong addition but does not cover the retrieval mechanics an agent needs.

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 0% across five parameters, so the description must compensate and does not. It never explains limit/offset versus the separate member_limit/member_offset pair, leaving the two-level pagination model entirely undocumented; 'page' is the only hint and it covers at most half the 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 and resource ('List a page of indexed attachment records') and names the retrieval model (paged). It is distinguishable from siblings like get_paper and get_chunk, which fetch single objects rather than inventories, though it never names those siblings explicitly.

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?

'archive inventories are bounded' implies paged retrieval and hints that callers should iterate, but there is no explicit statement of when to use this versus get_paper or get_chunk, nor any prerequisite about the required citekey (e.g., that it identifies a paper whose attachments are listed).

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