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

The description contradicts the annotations. Annotations declare readOnlyHint=true, implying the operation does not modify state, but the description says 'Start an asynchronous export' which launches a job and side effects (creating an export). This is a serious inconsistency that could mislead an agent into assuming no side effects. Beyond the contradiction, the description adds some useful behavioral context (opaque jobId, don't expose to user) but fails to disclose any permission or rate-limit requirements, and the contradiction dominates.

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?

The description is two sentences, front-loaded with the core action ('Start an asynchronous export'), and packs essential operational details (jobId polling, internal vs natural names, don't expose jobId) without waste. Every sentence adds necessary information for correct invocation.

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?

Given the asynchronous nature, the description covers the key interaction pattern (poll with jobId) and the privacy requirement (don't show jobId). The output schema presumably documents the jobId return, so its absence here is acceptable. However, it omits any mention of errors or prerequisites (e.g., document must be saved), and does not address concurrency or rate limits. The schema covers format options, so completeness is reasonably high, but not exhaustive.

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 description adds meaning beyond the schema by stating that natural workspace names and document titles are accepted and that internal routing identifiers are optional. This clarifies the dual-identification approach and reinforces which parameters to prefer, going beyond the schema's descriptive comments. With 80% schema coverage, the baseline is 3, but the description's explicit guidance on when to use which identifier adds value.

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 clearly states the action (start an asynchronous export) and the resource (current saved document). It also distinguishes itself by noting the asynchronous nature and the presence of a jobId for polling, which is not mentioned in sibling tools like convert_document or render_article. The purpose is specific and unambiguous.

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 guidance on how to use the tool after invocation: pass the jobId to get_article_export_status and never show jobId to the user. It also hints at parameter selection by mentioning natural workspace names and document titles are accepted. However, it does not explicitly state when to prefer this over alternatives like convert_document or render_article, leaving the when-to-use versus siblings implicit.

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