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

Annotations already declare idempotentHint=true and destructiveHint=false, so the description earns credit for the genuinely non-obvious detail: deleted stories are re-linked only if still unassigned, and a story reassigned meanwhile stays put. It also names the relinkedStoryCount return value, which is the only handle an agent has given there is no output schema.

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?

Three short sentences, front-loaded with the action, then the cascade rule, then idempotency. No filler and no repetition of the schema or annotations.

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 one-parameter mutation with no output schema, the description covers the action, the side effects on related stories, the returned count, and retry safety. Nothing an agent needs to call it correctly is missing.

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 100% with a single required epicId, so the schema fully carries parameter meaning and the description adds nothing beyond it. Baseline 3 applies; a note such as 'epicId must reference a soft-deleted row' would have raised this.

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 ('Restore a soft-deleted epic'), and 'soft-deleted' usefully narrows it to the undo path. It does not explicitly name a sibling such as delete_epic or update_epic, but the restore_* family and the resource noun make it 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?

Usage is implied rather than stated: an agent can infer it should call this when an epic was deleted and needs undoing, and the idempotency note tells it retrying is safe. There is no explicit 'use this instead of X' guidance or prerequisite/permission statement.

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