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

Annotations declare the mutation profile (readOnlyHint=false, destructiveHint=false), and the description adds real context on top: it creates the show's OndaCast page and is subject to per-client, per-day addition limits. What happens on a duplicate add is left to the idempotentHint=false annotation.

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?

Three front-loaded sentences with zero filler: what it does, where the id comes from, the input constraint, then the quota. Each clause carries information the agent needs.

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?

Single required parameter fully documented in both schema and prose, output schema present so return values need no explanation, and rate-limit/mutation behavior disclosed. Nothing an agent needs to call this correctly is missing.

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 100%, but the description still earns its place by clarifying a common failure mode: 'It takes no web address: only directory ids such as itunes-123 or pi-456', giving concrete id shapes beyond the regex in the schema.

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 specific verb and resource ('Add a podcast from a public podcast directory to OndaCast') and ties the input to the sibling that produces it. An agent can immediately tell this apart from the read-only search_* and get_* 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?

Explicitly names search_podcasts and the notOnOndaCastYet field as the source of valid ids, and flags this as 'the only tool that changes anything', which routes the agent correctly among siblings. It stops short of stating when-not-to-use cases (e.g. already-added shows, private feeds).

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