Register standing source

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

Goes well past the annotations (readOnly=false, idempotent=true, openWorld=true): it discloses that no network call happens at registration, that a detection cursor is created and the resident scheduler polls later, and that duplicates return the existing source unchanged with created=false. It also flags the consent-off default and the required dashboard confirmation, which the annotations cannot express.

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?

Four sentences, each carrying a distinct load: purpose, sibling routing, behavioral mechanics, duplicate semantics, consent hand-off. The key constraint (consent off) is front-loaded in the first clause and nothing is repeated.

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 4-param mutation with no output schema, the description covers what an agent needs: it explains the cursor/no-network behavior, the duplicate return value including the created flag, and the consent prerequisite. There is no output schema to describe, and the mutation's side effects are already disclosed.

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 url, kind, display_name and poll_interval_min are already documented in structured data, and the baseline applies. The description does add adjacent meaning — the scheduler-polls-later note clarifies that poll_interval_min is not a first-call deadline — but it does not add syntax or format detail beyond that.

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+resource ('Register a standing source') and immediately scopes it ('for future metadata detection with capture consent off'). It also names the exact siblings it is not (add_podcast_feed, add_monitored_playlist), so an agent can distinguish it from the crowded podcast/playlist tool family without opening a schema.

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 routing: use this for the 'general source workflow', use add_podcast_feed or add_monitored_playlist 'when you need their feed or playlist IDs'. It also names set_source_consent as the follow-up path once consent is confirmed, so the agent knows both the alternative and the complement.

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