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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the description does not need to restate those. It adds useful behavioral context: the pack is bounded to twelve records, includes citations, is produced in Markdown or JSON, and does not generate claims or save a publication. No contradiction with annotations exists.

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 sentence delivers the core operation, constraints, output format, and key non-goals without filler. The most decision-relevant information is front-loaded, and every clause earns its place.

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 description is adequate for basic selection but leaves gaps: there is no output schema, yet the return structure of the 'pack' is only vaguely described as Markdown or JSON. The meaning of the 'generation' parameter and how 'max_chars' affects output are not addressed, so an agent may still be unsure about invocation details.

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?

The schema has 0% description coverage, so the description carries the burden of explaining parameters. It only loosely maps to 'ids' via 'up to twelve published records' and to 'format' via 'Markdown or JSON pack'. The 'max_chars' and especially 'generation' parameters are not explained at all, leaving the agent to guess their meaning.

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 names a specific verb ('Assemble'), a clear resource ('up to twelve published records with citations'), and an output format ('bounded Markdown or JSON pack'). It also distinguishes itself from the sibling retrieval tools by stating it packs existing records. The explicit non-goals ('Does not generate claims or save a new publication') further sharpen the purpose.

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 description provides clear context for when to use the tool: to assemble published records into a bounded pack. It also gives implicit when-not guidance by stating it does not generate claims or save a new publication. It does not explicitly name or contrast sibling tools like get_evidence or search_evidence, so it stops 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.