proofpage_verify_quotes

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

With no annotations, the description carries the full load and does disclose key behavior: collect_missing=true is an explicit authorization for public-page collection and it queues a durable job that outlives the request. That is meaningful side-effect disclosure an agent could not get from the boolean schema. It stops short of describing cost/latency, failure modes, or what happens when collection is unauthorized.

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?

Two sentences, no filler. The batch limit and the highest-stakes flag (collect_missing authorization) are front-loaded, and the follow-up routing instruction follows immediately.

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?

No output schema and no annotations, yet the description supplies the asynchronous job model and the follow-up tools, which is the main thing an agent would otherwise get wrong. It omits what a 'check' yields (per-citation match/verdict) and any indication of latency or batching, which are minor given the step/get routing it already provides.

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 0%, so the description must compensate, and it does: 'citations' is characterized as explicit {url, quote} pairs capped at 50, and 'collect_missing' is given real semantics (authorizes public-page collection, queues a durable job). The gap is that collect_missing=false behavior is only implied by contrast.

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: 'Check up to 50 explicit {url, quote} pairs', which tells an agent exactly what the tool consumes and does. It also implicitly positions itself as the initiator relative to the step/get siblings ('use step/get tools to advance it'), though it does not name proofpage_step_quote_check or proofpage_get_quote_check explicitly.

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 clear usage context: batch limit of 50, and that advancing a queued job requires the step/get tools rather than the desktop server. It does not state when NOT to use it (e.g., for non-explicit or discovered URLs, where proofpage_search or proofpage_add_source might be the entry point), leaving that inference to the agent.

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