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

Annotations declare destructiveHint=true and openWorldHint=true; the description adds real substance beyond that — 'Saving drops any approval', queued/filming/delivered episodes keep their rows, and unrewritten later rows become needs_rewrite. Minor gap: it does not say what happens on revision mismatch with expected_revision or whether the write is transactional.

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?

Everything stated is load-bearing given a zero-coverage schema, but it is delivered as one dense wall of semicolons and nested parentheses, so the ordering rules, sizing rules and episode-field spec blur together. The critical 'BEFORE create_series' constraint is front-loaded, but the rest would read far better as discrete sections.

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 destructive, seven-parameter tool with nested arrays and no output schema, the description covers inputs, invocation ordering, side effects, and even lists the return fields (revision, content_hash, say, size_status, warnings, next). An agent has essentially everything it needs to construct a valid call and predict the outcome.

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 both size and episodes are untyped nested objects, so the description carries the full burden and does: it defines size as {episodes, seconds, quality}, gives the minimum for season_plot (15 words), and enumerates every episode field with its allowed values (cliffhanger_type options, tension 1-10, payoff none|small|major, optional cast/locations/gag/guests) plus the finale requirement. Only the optional 'title' parameter is never explained.

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?

Opens with a specific verb+resource ('Save the season plan') and immediately positions it against the paid sibling ('BEFORE the paid create_series'), which is exactly the disambiguation an agent needs. It also states a distinguishing behavioral fact ('Free, generates nothing') that separates it from create_series and the generate_* tools.

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 explicit ordering (save before create_series) and conditional sourcing rules: in series_interview use brief.size, otherwise exactly what the customer chose from get_season_options with no default. It also names the prerequisite for replacement (expected_revision) and the consequence of locked sizes, so the agent knows when this call is legal versus premature.

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