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

Annotations already declare readOnly/idempotent/non-destructive, yet the description adds substantial behavioral context: that the call can block while waiting, that progress notifications are emitted, that images_pending text is final and will not change, and that failed images cannot be retried through this server. It also flags the untrusted_source_text wrapping, which is critical safety context an agent needs.

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?

Content is front-loaded with purpose, then waiting, then paging, then return details. Four short paragraphs are slightly longer than strictly necessary and some return-field detail overlaps the output schema, but each sentence conveys real operational information.

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?

For a polling-and-paging read tool, the description covers job states, truncation/pagination, waiting semantics, partial-image behavior, and the untrusted-content boundary. With an output schema present it need not document return fields, yet the extra polling and safety context makes the definition complete for correct invocation.

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, but the description adds genuine meaning beyond the raw schema: wait_sec is explained as blocking inside the call, include_transcript is described as appending the full timed transcript, and offset is tied to the next_offset pagination token. It does not clarify max_chars behavior beyond the schema.

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 first sentence gives a specific verb (Returns), resource (an article created with create_article), format (Markdown) and accompanying state (its status). The agent can immediately distinguish this retrieval tool from its write sibling create_article and the other get_* tools.

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?

It clearly frames the polling workflow (wait_sec waits inside the call for the text to be ready) and the paging workflow (when truncated is true, call again with offset set to next_offset). It stops short of explicitly naming when to prefer a different sibling or a when-not condition, but the context for use is unambiguous.

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