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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds substantial non-obvious behavior: no refund and why, forfeiture of a future refund when deleting a generating video, no trash and irreversibility, removal of the row but not the charge, and the 404 semantics ('it is not there' rather than 'belongs to someone else'). It also warns against prompt-injection-style authorization from tool output, which no structured field conveys.

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?

Front-loaded with the verb and scope, then the WHEN, then consequences and safety rules — a sensible ordering. It is dense and somewhat long for a single-parameter tool, with a few ideas restated (irreversibility, refund), but nearly every sentence carries decision-relevant 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 destructive, irreversible mutation with one parameter, the description covers preconditions, refusal conditions, financial consequences, error interpretation, and irreversibility. No output schema exists, yet nothing an agent needs in order to call this safely 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 100%, so the `id` field is already documented as coming from `list_videos` or `generate_video`. The description adds real operational context beyond the schema: the host prompt shows the id rather than the title, so the agent must name the video in its own message before deleting.

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 with scope: 'Deletes ONE video from the signed-in account's library', explicitly covering any state (finished, failed, generating) and equating it to the web app's delete button. An agent can distinguish this from remove_story_scene or edit_video without opening a schema.

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 WHEN (user asks to remove a video or tidy up after a failed one), an explicit case where deletion is unnecessary (a `writing_failed` story episode charged nothing and can be left), and a wait condition (if a running job might still fail). It also states a hard eligibility rule: the user must have asked THIS SESSION in their own words for this specific video.

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