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

Annotations carry no read-only or destructive hints, so the description carries the burden. It adds meaningful behavioral detail: the result is a short-lived URL, and it frames the operation as a standard, non-publishing step. It does not contradict annotations, though it omits explicit side-effect disclosure (e.g., whether the job is modified), which is a minor gap.

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?

Two sentences deliver all necessary information: the action, formats, return type, usage preferences, and an exclusion. The most critical facts are front-loaded, and there is no redundant or filler content.

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 tool with 3 parameters (2 required, one enum) and an output schema, the description covers the essential call-time details: what it does, output format, URL lifetime, and usage routing. The missing run_id explanation and lack of explicit side-effect notes are minor gaps, but the presence of an output schema reduces the need to describe return structure.

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 0%, so the description must compensate. It explains the format parameter thoroughly with per-format usage context, and job_id is implicitly clear as the job to export. However, the optional run_id parameter is not mentioned at all, leaving its purpose ambiguous for an agent, though its optionality reduces the impact.

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 uses a specific verb ('Export') and resource ('a job'), lists the three output formats (pdf, html, png) with their packaging details, and states the return value (short-lived download_url). It distinguishes itself from siblings by explicitly noting it is the 'standard download step' and contrasting with publishing, making its purpose 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 gives explicit format-selection guidance ('Prefer pdf for print/slides/cards; html for web landing pages; png when the user wants images') and a clear exclusion ('do not publish unless the user asks'), telling the agent exactly when to use this tool and when to avoid alternatives like publish_design.

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