Discover capture candidates

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

Goes well beyond the annotations: discloses that the call spends credits, requires agent discovery consent or a process-bound dashboard intent (with stdio caveat), and crucially that 'no candidate is captured by this call' — clarifying that the readOnlyHint=false flag does not mean it mutates the library. That is the exact ambiguity the annotations leave open.

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 purpose and routing, and every sentence carries operational information. The consent sentence ('Spending requires agent discovery consent or a dashboard intent; stdio needs agent consent because dashboard intents are process-bound') is dense and slightly convoluted, costing a point.

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 purpose, alternatives, prerequisites, cost model, consent requirements and the no-capture guarantee for an 8-parameter open-world tool with no output schema. What remains implicit is the shape of the returned plan (credits_planned etc.), though 'confirm its exact cost' hints at it.

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 the baseline is 3; the description adds genuine meaning by explaining the confirm_credits handshake (omit for a free plan, then confirm its exact cost) and by contrasting user_intent_token with the stdio consent setting. It does not add per-parameter detail for mode/platform, but the schema already handles those.

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 concrete verb+resource pair: plans or runs a ScrapeCreators search and saves uncaptured candidates. It also names the two adjacent siblings (search_library for saved evidence, queue_discovered for capturing) so the agent can route 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?

Explicitly says when to use this ('to find new material'), which alternatives to use instead (search_library, queue_discovered), and the preconditions (saved key, discovery enabled, daily credit room, off by default). The free-plan flow via confirm_credits is spelled out as a two-step procedure.

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