next_inspiration

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

With no annotations, the description fully discloses behavioral traits: it marks the post as seen (mutation), returns a ChatGPT Apps SDK widget with specific content, and that the image is delivered via the widget for rendering. It also explains the sequential walking through unseen posts.

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?

Three sentences, each earning its place: first defines purpose and side effect, second describes return widget content, third gives usage pattern and sibling reference. No fluff, highly efficient.

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 no parameters, no output schema, and no annotations, the description is thoroughly complete: it explains the action, return type, side effect, widget rationale for rendering, and references a sibling for resetting. Covers all necessary context.

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?

There are zero parameters, and schema coverage is 100% vacuously. The description needs no parameter information; it sufficiently explains what the tool does without input, making it clear no parameters are required.

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 tool shows 'one not-yet-seen post for inspiration' and marks it seen. The verb 'show' and resource 'post' with the qualifier 'not-yet-seen' precisely defines the action, distinguishing it from siblings like reset_seen.

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 explicitly says 'Calling repeatedly walks through unseen posts; use reset_seen to start over.' This provides when to use (get next inspiration) and when to use an alternative (reset_seen), giving clear usage context.

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