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

Goes well beyond the annotations by disclosing cascading consequences: later episodes are marked needs_rewrite, previously saved scripts become stale and must be re-saved before filming, and the approval is dropped. It also states the refusal preconditions and that the operation is free and produces no generation — none of which the annotations convey.

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?

Front-loads the distinguishing facts (free, no generation, replaces one episode) and packs the cascade warnings into one dense sentence with no filler. The long middle clause is run-on and could be split for scannability, but every sentence earns its place.

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?

Given a mutation tool with a nested object parameter and no output schema, the description covers scope, preconditions, side effects and refusal states well. The remaining gap is post-call state — nothing says what revision the plan ends up at or what the response contains after a successful replace.

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%, so the description must carry the load: it explains expected_revision as an optimistic-concurrency guard ("must be the current revision") and defines episode by reference to a save_season_plan episode. series_id and n are left to implication, which is reasonable but not complete.

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 precise verb and resource ("Replace episode n of the season plan") and pins down the payload shape by reference ("same fields as one save_season_plan episode"), which distinguishes it from save_season_plan and from read siblings like get_season_plan without requiring the schema to be opened.

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?

Gives clear operative conditions: expected_revision must be current, later episodes must be rewritten "with this tool", and calls are refused when episode n or later is queued, filming or delivered. It does not explicitly contrast with save_season_plan for a full-plan rewrite, but the per-episode scope makes the choice inferable.

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