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

No annotations are present, so the description carries the full behavioral burden. 'Return' clearly signals a non-destructive read and scoping to one episode, which is useful, but it discloses nothing about failure modes (unknown code/title), what happens with ambiguous or partial input (e.g. season alone), or auth/rate limits.

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 tight sentences: the first front-loads what is returned, the second the accepted inputs. No filler, and the most decision-relevant information (scope + identifier forms) leads.

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?

With no output schema, enumerating the returned fields is exactly the right compensation, and no annotations mean little extra disclosure is strictly required for a simple read tool. The only real gap is behavior for unmatched or ambiguous input.

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 already 75%, and the description adds meaningful semantics by showing the code format (S03E12) and indicating that season+episode or an exact title are valid alternative identification paths. It stops short of explaining how the four optional parameters interact or which combination takes precedence.

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 concrete verb ('Return') and resource ('everything this site records for one episode') and enumerates the payload (summary, air date, writers, directors, viewing figure, identifiers). It reads as a single-record lookup distinct from search_episodes or get_season, though it never explicitly contrasts itself with those siblings.

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: the description lists three accepted identifier forms (code, season+episode, exact title) but gives no when-to-use guidance, no conditions that select this tool over search_episodes or which_episode, and no note about tie-breaking or no-match behavior.

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