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

Annotations already declare readOnly/idempotent/non-destructive, so the safety bar is low; the description still adds real value with 'Owner only' (an authorization constraint absent from annotations) and 'the real result never changes', which clarifies the replay is a sandbox rather than a mutation.

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 sentences, front-loaded with purpose and the sandbox guarantee, then the enum glossary. The parenthetical mode definitions are dense but each earns its place; nothing is padded.

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?

No output schema exists, so the description should carry the return contract, yet it only says the outcome 'would differ' without indicating what the comparison actually returns. Combined with an undocumented episode_id, this leaves an agent slightly under-informed for invoking correctly.

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 only 33% and the enum values carry no schema descriptions, so the description's inline glossary for bolder/safer/long_game genuinely compensates — a reviewer can choose a mode without guessing. It misses only bigger_budget and gives no hint about episode_id.

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 states a specific verb (replay), resource (one of your dates), and the distinguishing twist (a single thing changed, to compare outcomes) — enough to separate it from siblings like get_episode or reflect_on_date. The opaque tool name 'sliding_doors' is fully rescued by the description, though it never names a competing sibling.

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?

'Owner only' states a prerequisite and the purpose ('compare how the outcome would differ') implies when to reach for it, but there is no explicit when-not guidance and no alternative tool is named (e.g. versus reflect_on_date for genuine post-date analysis). Usage is inferable rather than stated.

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