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

Annotations already carry the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=true), so the description's added value is what happens on bad input — unknown keys are rejected atomically and nothing is persisted — plus the tenant scope ('for the caller's merchant'). It does not explain what overwriting an existing metadata value implies, which is the one behavior an agent might still want given destructiveHint=true.

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 core action, no filler. The parenthetical packs the field list and the ID keys densely, but every clause (field whitelist, ID lookup, atomic rejection, sibling routing) 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 3-parameter mutation with a nested free-form object, no output schema and zero schema descriptions, the definition covers the whitelist, identifier resolution, failure semantics and the sibling boundary. Remaining gaps (response shape, identifier precedence, permission requirements) are modest but real.

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 0% and `updates` is a free-form object with additionalProperties=true, so the description's enumeration of permitted keys is the only documentation that exists — a substantial compensation. It also explains that video_id and video_uuid are alternative identifiers, though it never says whether one is required, whether both may be supplied, or what happens if neither matches.

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?

Specific verb plus resource ('Update only the metadata of a video') with the exact editable fields enumerated (title, description, language, keywords) and the two lookup keys named. It also distinguishes itself from render_video, so an agent can pick it out of a very large sibling set 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?

Explicitly bounds the tool ('only the metadata', 'any other key is refused and nothing is written') and names the alternative for the excluded work: 'The timeline, output and render queue are changed with render_video.' That is a clear when-to-use / when-not-to-use / use-instead triple.

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