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

Annotations declare the tool as read-only and idempotent (readOnlyHint, idempotentHint, destructiveHint=false), so the agent already knows it's a safe query. The description adds value by enumerating exactly what the response contains (passage, narrative, theories, proponent and sources, confidence rubric, FAQs), giving the agent a clear picture of the output without needing to inspect an output schema. No risky behaviors (e.g., side effects, write actions) are implied, so the description aligns with and supplements the annotations.

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?

The description is one dense but well-organized sentence that leads with the operation ('Get one episode by slug'), enumerates the output contents, and ends with a usage condition. No filler words; every clause adds information. This is efficient and front-loaded.

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 getter with a single required parameter, the description covers what is returned and when to use it. The annotations already cover safety (read-only, non-destructive), and the schema documents the optional locale. The description doesn't mention potential error cases (e.g., invalid slug) or response structure, but the output content is enumerated. It is reasonably complete for a read-only tool.

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?

The schema fully covers both parameters with descriptions and an enum for locale (e.g., 'slug' with example). The description adds only the context that a slug selects the episode, which is already implicit in the parameter name and type. Since schema coverage is 100%, the description provides no additional semantic value for the parameters themselves, warranting the baseline score.

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 ('Get'), the resource ('one episode'), and the inclusion of contents (passage, narrative, theories, etc.). It also provides an explicit usage condition ('when the question is where an episode took place and who argued for it'), which distinguishes it from sibling tools without needing further inference.

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 a clear contextual cue for when to use this tool: 'Use this when the question is where an episode took place and who argued for it.' While it doesn't explicitly contrast with alternatives like 'search' or 'list', the instruction provides a functional gate and implies the need for a specific slug. This is more guidance than the example 'update_drive'.

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