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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real behavioral detail beyond that: result ordering is newest-first, each item carries state and file links, and results are scoped to this app's creations on the user's account. Pagination behavior is only implied by the before_id param rather than stated.

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, front-loaded with the use case and closed with the sibling routing, with no filler. The first sentence is dense with comma-joined clauses (media kinds, ordering, state, links) but each clause carries information an agent needs.

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?

An output schema exists, so return values needn't be spelled out, yet the description still summarizes what comes back (state and file links). For a simple, zero-required-parameter read tool, nothing needed to call it correctly is missing.

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 only 33% — just before_id is documented — so the description must carry more weight. It partially compensates by naming the three media kinds (mapping to the type enum) and by stating newest-first ordering, which relates to the cursor, but it never explains limit bounds or how before_id pagination is meant to be used.

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?

States a specific verb and resource — lists the images, videos and voice-overs this app created on the user's Deepnia account — plus ordering (newest first) and payload (state and file links). It is clearly separable from create_* siblings and from get_creation, which it explicitly routes to.

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?

Gives an explicit trigger ("when the user asks what they already made through this app, or an earlier creation's id or link is needed") and names the alternative for a different need ("To follow a creation just started, call get_creation"). The when-to-use and when-not-to-use split is unambiguous.

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