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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds two pieces of context beyond that: the deletion is scoped to the caller's own subtitles (an authorization boundary) and should only happen on explicit request. It doesn't state permanence or recovery options, but that is largely implied by destructiveHint.

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 front-loaded sentence with no filler; the verb and resource come first and the conditional guard follows. Nothing could be removed without losing 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?

An output schema exists, so return values need no explanation, and annotations cover the destructive/idempotent profile. However, for a destructive single-parameter tool the description leaves the key input (storage_path) and the permanence of deletion unaddressed, which is a meaningful gap.

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 is one required parameter, storage_path, with 0% schema description coverage, and the description says nothing about it — not its format, where it comes from, or whether it is the same path returned by list_subtitles. With the schema silent, the description needed to compensate and does not.

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 ('Delete a saved subtitle') plus an ownership scope ('belonging to the caller'), which cleanly separates it from the sibling delete_* tools that target voices, style guides, and translation memory entries. It stops short of naming an alternative, but the resource is 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 clause 'when explicitly requested' gives a real usage guard — the agent should not delete proactively — but no alternatives or preconditions are named, and it doesn't say what to do if the caller is unsure which subtitle to remove.

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