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

Annotations already mark readOnlyHint=false and destructiveHint=false, and the description adds meaningful behavior: the operation is asynchronous, returns a job id, must be polled until completed, and exposes result.url. It explicitly guarantees no user data is touched and nothing can be deleted. It could add failure or status details, but this is strong coverage beyond annotations.

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?

Four sentences, all high-signal: purpose, workflow, when-to-use, and safety. Front-loaded with the core action, then proceeds to actionable details without redundancy.

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 supplies the needed contract: returns a job id, poll until completed, read result.url. Together with full parameter schema and use-case guidance, an agent has enough to call and process the result correctly.

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 already has 100% description coverage, including enums for resource and format and a clear idempotency_key description. The tool description repeats those values but does not add meaningful new semantics beyond mapping the async workflow to the parameters. 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?

Description starts with a specific verb-resource pair: 'Start an asynchronous export of a Yappy corpus', then enumerates the corpus types (documentation, FAQ, release history) and output formats (markdown, JSON). It also names the polling sibling get_export_job, which clearly distinguishes this job-creating tool from the read-oriented siblings.

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?

Provides an explicit use condition: 'Use it when you want the whole corpus rather than a page at a time', which implies not for single-page grabs. It also routes the agent to get_export_job for polling and clarifies the tool creates a job and nothing else, giving a clear boundary versus other data-access tools.

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