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

Goes well beyond the annotations: discloses asynchronous/background execution, that the response returns only a count, per-lead AI credit consumption, an API key requirement, that leadIds re-bills already-scored leads, and the 200-id cap. This is exactly the behavioral context annotations cannot convey.

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 short, front-loaded paragraphs, each carrying a distinct operational fact (scope selection, async behavior, cost/auth, rescore semantics) with zero filler.

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 exists, yet the description explains the return value (an immediate count, not scores) and the follow-up read path. Combined with cost, auth, and cap disclosure, an agent has everything needed to call this correctly.

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 already 100%, so baselines is 3, but the description adds real meaning: jobId targets only unscored leads while leadIds rescores regardless of existing score (with billing implications), plus the 200 cap and the either/or constraint.

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 ('Queue AI qualification scoring for leads') and immediately delineates the two disjoint scopes: every unscored lead in a job, or a specific id set. This distinguishes it cleanly from scoring-adjacent siblings like enrich_lead or list_leads.

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 states the mutual exclusion ('Pass jobId OR leadIds, not both'), when to prefer one over the other ('pass jobId to score only what is unscored'), and how to retrieve results afterwards ('re-read them with list_leads'). Nothing is left to inference.

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