Poll podcast feed

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

Adds real context beyond the annotations: polling records observations, managed sources honor detection due times and leases, and capture remains subject to separate source consent and scheduling. This explains the non-idempotent, open-world side effects that readOnlyHint=false / idempotentHint=false only imply. It stops short of clarifying what a 'feed error' looks like or what happens when a lease is held, so not a full 5.

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 purpose and the primary alternative are front-loaded in the first two sentences, and each subsequent sentence adds distinct operational information. Some phrasing is jargon-heavy ('source-aware polling path', 'capture remains subject to separate source consent') which costs a little clarity without wasting much space.

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?

Covers the essential loop for a fetch-triggering tool: what it returns ('the poll outcome or a feed error'), that observations are recorded, and that consent/scheduling gates downstream capture. With no output schema, that return statement matters, though the shape of the 'poll outcome' is left vague.

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 100% and the feed_id description already explains where the integer comes from. The tool description only reinforces 'one registered podcast feed' and adds no format or validation detail beyond the schema — the baseline 3 for high-coverage single-param tools.

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 (refresh metadata) and resource (one registered podcast feed) plus the execution path (source-aware polling). It also distinguishes itself from the closest sibling by noting that list_podcast_episodes reads cached episodes without a fetch, so an agent can choose between them without opening schemas.

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?

Explicit lifecycle guidance: 'Use after add_podcast_feed when new episode observations are needed,' with a named alternative and the exact condition that selects it ('use list_podcast_episodes to read cached episodes without a fetch'). Both the when and the when-not are stated.

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