Queue discovered posts

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

Goes well beyond the annotations: it discloses the skip semantics (unknown, unsupported, captured, or queued URLs are skipped), the queued/skipped return shape, the fact that no ScrapeCreators credits are spent, and that capture is deferred to a resident retry worker. The one gap is that idempotentHint=true is not reconciled with the queued-vs-skipped behaviour (i.e., re-queueing an already-queued key is silently skipped rather than erroring), though the skip list implies it.

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?

Front-loaded with the action and the predecessor tool, then preconditions, then returns. The consent sentence ('Requires agent discovery consent or a dashboard intent; stdio needs agent consent because dashboard intents are process-bound') repeats itself somewhat and could be tightened, but every clause carries operational information.

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 non-destructive, idempotent enqueue tool with no output schema, the description covers inputs' provenance, preconditions, what is skipped and why, cost implications, and when capture actually happens. An agent has everything needed to call it correctly on the first attempt.

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%, so all three parameters are already documented, including the 'not a Librarian run ID' disambiguation. The description adds only that picks are 'selected' candidates and that the intent is dashboard-bound, which the schema already states — baseline 3 is appropriate.

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 — 'Enqueue selected saved discovery candidates for normal capture' — and immediately names discover_candidates as the source of the run and keys, so an agent can place it precisely in the discovery→capture pipeline rather than confusing it with the search step.

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?

Gives explicit sequencing ('Use after discover_candidates returns a run and candidate keys') and explicit re-routing for the alternative case ('use that tool again to search for new candidates'). It also states the precondition (agent discovery consent or dashboard intent) and the stdio caveat, leaving little to inference.

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