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

Annotations already declare destructiveHint=true, readOnlyHint=false, and openWorldHint=true, so the mutation profile is covered. The description adds precondition context (only failed or cancelled tasks can be retried), but says nothing about side effects of re-running, idempotency, or whether a new task is spawned instead of resuming — a real gap for a mutation tool.

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 wasted words, appropriate for a one-parameter tool. It is efficient, though minimal — nothing is padded but nothing extra is provided either.

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 task-lifecycle mutation with a completely undocumented required parameter and no output schema, the description is too thin. It omits how to obtain taskId, what states are retryable, and whether the retry returns a new task identifier — information the structured fields do not supply.

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% for the single required taskId parameter, and the description never mentions it. The agent gets no format, source, or lookup hint for taskId from any field, so the description fails to compensate for the coverage gap.

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 (failed or cancelled background task), which is clearer than a bare restatement. However, it does not differentiate from the many sibling retry_* tools (retry_message_target, retry_pending_comment, retry_pending_reply, retry_post_target), so an agent cannot tell from the text alone whether the generic task retry is the right one.

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 phrase 'failed or cancelled' implies the precondition for using it, giving implicit usage guidance. But there is no explicit when-to-use vs. when-not, and no mention of alternatives among the four retry_* siblings, so routing is left to inference.

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