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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the bar is lower. The description adds real behavioral context beyond annotations: results come from a fresh run rather than cached data, failure yields fresh_discovery_count: 0 with no fallback substitution, and the operation is draft/review only. 'Fresh' also aligns internal with idempotentHint=false. No contradiction with annotations.

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?

Three sentences with zero filler: purpose, failure behavior, and side-effect boundary. The most decision-relevant constraint ('does not substitute the existing review queue') appears in the second sentence, and every clause earns its place.

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?

The output schema exists so return values don't need explanation, and annotations cover the safety profile. The description handles purpose, failure mode, and side-effect bounds adequately. Its residual gaps — undocumented meanings for lane/sources/min_score and no explicit guidance on when to prefer sibling discovery tools — leave it just short of complete.

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 only 44%, so the description must compensate. It adds useful framing that gives meaning to query (plain-language search for manually reviewable roles), and include_tracked and allow_live_firecrawl have good inline schema descriptions. However, lane (J vs C semantics), sources, and min_score remain unexplained in both schema and description — a genuine gap for a 9-parameter tool.

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 ('Run fresh governed public-opportunity discovery') and the intended outcome ('find roles they may review and apply to manually'). The phrase 'does not substitute the existing review queue' explicitly separates it from sibling talent_scout_review_queue and related discovery tools, so an agent can distinguish it without opening 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?

Makes the trigger context explicit (fresh discovery for manual review) and spell out the failure behavior ('If live discovery is unavailable or empty, returns fresh_discovery_count: 0'). It states exclusions behaviorally ('never applies or sends messages', doesn't substitute the queue) but does not name alternative sibling tool explicitly, which keeps it at 4 rather than 5.

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