mark_episode_played_plan

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

With no annotations provided, the description carries the full disclosure burden, and it delivers thoroughly. It reveals the non-obvious behavior that despite the name 'mark_episode_played,' nothing is executed or mutated, states 'Read-only by design,' explains the root cause (removed API, issue #230), and describes the internal mechanics (fetch resume points, compute seek targets). This is exactly the kind of behavioral context an agent needs and cannot infer from the name or 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?

Two dense sentences with zero filler. The critical warning 'never execute' is front-loaded before anything else, followed by the reason, the mechanism, and the read-only guarantee. Every clause earns its place and the structure ensures the most decision-relevant information is seen first.

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 2-parameter tool with full schema coverage, the description is nearly complete: it explains what the tool does, what it deliberately does not do, and what the output represents (target positions to seek to). The only minor gap is that it does not preview the shapes of the response_format variants, but since there is no output schema and the parameter enum is self-documenting, this omission is acceptable rather than critical.

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 100%, so both episode_ids and response_format are already well-documented with types, ranges, formats, and enums. The description adds slight semantic context by linking the episode_ids to 'episodes to mark fully played' and the outputs to seek positions, but it does not need to compensate for any schema gap. Baseline 3 is appropriate.

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-resource pair: it 'plans which episodes to mark fully played.' It differentiates itself from the many mutation siblings by leading with 'never execute' and clarifies the mechanism ('fetches current resume points and outputs the target positions the player would seek to'). An agent can immediately understand what this tool produces and how it differs from an actual mark-played mutation.

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 description gives explicit context for when this tool is appropriate: it is a plan-only tool because 'Spotify removed the mark-played API, issue #230,' and instructs 'never execute.' This is a strong when/when-not signal. It stops short of naming a specific sibling alternative for actual execution, but the constraint is so unambiguous that an agent will not misuse it as a mutation tool.

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