export_atlas

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

Annotations already declare destructiveHint=true and idempotentHint=false, so overwrite/non-repeat behavior is signaled structurally. The description adds real value beyond that: the finished-run+verdict precondition, the per-paper error listing on render failure, and the licence requirement. It loses a point only because the desktop-app/licence requirement is stated twice rather than once.

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?

Core function is front-loaded and readable, but the leading app-installation paragraph and the trailing 'Requires an Atelier or Portfolio licence' restate the same availability constraint, and the 'N reports is N trials' aside is tangential. There is noticeable redundancy that dilutes an otherwise tight description.

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 usefully enumerates the return fields (ok, dir, n, papers, failed) and what a per-paper entry contains, and covers the key preconditions. It is nearly complete; only the duplication and lack of pagination/limit nuance around large run_id batches keep it from a 5.

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%, and the schema already documents title, layout, out_dir and run_ids including the overwrite note on out_dir. The description repeats the shared-layout/shared-title idea but adds no syntax or format detail, so the baseline 3 applies.

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+resource with scope: 'Write one research paper PDF per finished run with a shared layout and title.' It explicitly distinguishes itself from the sibling export_paper, which handles a single run, so an agent can route without opening schemas.

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?

Gives a clear when-to-use ('report several runs consistently') and names the alternative ('export_paper handles a single run'), plus the precondition that every run must be finished and carry a verdict or nothing is written. Exclusions and prerequisites are explicit.

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