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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context beyond annotations: pagination by passage and the fallback pointer behavior for unindexed works. It doesn't describe the exact response format, but that is a minor gap given the read-only, idempotent nature already 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?

Three sentences with no filler: purpose first, paging instruction second, fallback routing third. Every sentence carries information an agent needs, and the structure front-loads the primary action before secondary guidance.

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?

The tool has moderate complexity with 3 parameters fully described in the schema, annotations covering safety, and no output schema. The description covers pagination, fallback behavior, and parameter usage. It stops short of describing the shape of the returned passages or error behavior, but for a read-only retrieval tool this is a minor omission given all other context signals are covered.

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 100%, so the baseline is 3. The description goes beyond the schema by linking from_seq and max_passages together as a paging mechanism, and by giving a concrete corpus key example ('arxiv:2310.12345') that reinforces the paper_key format. This adds relational meaning not present in the individual property descriptions.

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?

The description opens with a specific verb+resource combination: 'Return the full text of an indexed open-access paper by its corpus key'. It clearly distinguishes itself from paper_details (metadata), paper_fulltext_search (search), and paper_status by focusing on full text retrieval. The example corpus key format leaves no ambiguity about the target resource.

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?

Locates the tool precisely among siblings: it states when to use it (indexed papers), how to page via from_seq + max_passages, and what to do when the work is not indexed locally (use paper_search / paper_details for an open-access URL pointer). This is explicit when/alternative guidance, matching the highest bar.

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