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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, so the safety profile is covered. The description goes beyond them by disclosing the 409 failure semantics for ineligible platforms, the partial-retry behavior when one platform needs review, and a warning not to derive eligibility from legacy video status. It adds no auth or rate-limit context, and never references the Idempotency-Key behavior.

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?

Four short sentences, front-loaded with purpose before the eligibility rules and error codes, with no filler. The 'safe failed sibling' sentence is slightly dense and could be split, but it conveys a non-obvious partial-retry case worth the words.

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, open-world, 6-parameter tool with nested objects and no output schema, the description covers the critical decision inputs (eligibility, 409 conditions, legacy-status caveat) and implies the queueing outcome. It stops short of describing the success response shape or the idempotency-key reconciliation path, which matters for a non-idempotent retry.

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 already 83%, so the baseline is 3, but the description adds real meaning to `platforms` by stating the eligibility rule (confirmed failed, retryable, present in data.video.publishing.platforms) that the schema only gestures at. It says nothing extra about videoId or the target/settings objects, which the schema handles.

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?

The description opens with a specific verb+resource ('Retry confirmed failed video platforms') and immediately narrows scope to only explicitly named, confirmed-failed, retryable platforms. That scope statement is what separates it from publishVideo/scheduleVideo siblings, which operate on any publishable platform, so an agent can route correctly without opening the 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?

It gives explicit preconditions (must be confirmed failed, retryable, and present in data.video.publishing.platforms) and explicit exclusions (successful, queued/running, needs_review return 409), plus the partial-retry case. The one gap is that it never names a sibling to use instead when the platform isn't eligible (e.g., a status tool), leaving that step to inference.

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