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 structurally. The description adds real value beyond them with the sort order, the returned fields, and the cost note ('Free'), but says nothing about pagination behavior, whether drafts or failed items appear, or how many results are typically returned.

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?

A single compact sentence that front-loads scope and ordering, then cost, with no filler. Every clause earns its place.

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 one-parameter read-only listing, the description plus rich annotations tell an agent what it gets back (status and links) and in what order. It lacks only pagination/coverage detail, which is a minor gap for this complexity.

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 description coverage is 100% with a single documented 'limit' parameter (1–50, default 10), so the schema carries the semantics. The description adds no meaning about the limit, so the baseline 3 is appropriate.

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 account's most recent videos and ads') plus ordering ('newest first') and returned fields ('status and links'). It is clearly distinguishable from create_* and get_video siblings by being a recent-items listing, though it never explicitly contrasts with get_video.

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?

'Free' is a decision-relevant hint that this costs nothing, implying it is the cheap way to browse recent content, but there is no explicit when-to-use vs get_video or when-not guidance. The agent must infer that this is the right call for a quick recent-items scan.

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