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

Annotations already declare readOnlyHint=false, destructiveHint=true and openWorldHint=true, so the safety profile is covered. The description adds a meaningful trait beyond that: the retry 'creates an externally visible post', clarifying the consequence is public and externally observable. It still omits idempotency and prerequisite/repeat-retry 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?

Two short sentences, front-loaded with the action and followed immediately by the key consequence. No filler, nothing that could be cut.

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?

Covered: purpose and the externally-visible consequence. Missing for a destructive, open-world mutation: prerequisites for a valid retry, what happens if retried repeatedly, and any description of the publishId parameter. With no output schema, no return-value explanation is required.

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 0% and the description never mentions publishId or what value it expects. With only one parameter the name is largely self-describing in context, but the description adds no semantics beyond what the bare schema name already conveys.

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 (retry) and resource (clip publish record), and the 'failed' qualifier implies this targets existing failed publish records rather than creating new ones. It does not name the sibling it contrasts with (publish_clip), so it falls short of full sibling differentiation.

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 word 'failed' implies the trigger condition (a prior publish that did not succeed), giving implied usage. However, there is no explicit when-not guidance, no prerequisites (e.g. whether the record must still be in a retryable state), and no named alternative such as publish_clip.

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