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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lowered. The description still adds real behavioral context: the inputs_unconfirmed flag on extraction, claims grounded or marked insufficient_evidence, mechanism-plausibility flags, and version metadata. It omits any mention of latency, cost, or failure modes for an open-world call.

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, front-loaded with the core verb and output shape, then input modes, then non-goals. No filler and every clause carries instruction or boundary 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?

With an output schema present, return values need no elaboration, yet the description still summarizes the reasoning chain and meta block. Inputs, output character, and explicit non-goals (rNPV, autonomous verdict) are all covered for a two-mode tool.

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 baseline would be 3, but the description adds the either/or contract between `text` and `fields` (the schema does not enforce mutual exclusivity) and explains the downstream consequence of each path.

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 ('produce a CONDITIONAL READ on a drug asset') plus the domain purpose ('for deal triage'). It distinguishes itself from siblings like query_drug_risk and get_dossier by naming the reasoning-chain and provenance character of the output.

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 pass `text` (teaser/abstract, mark inputs_unconfirmed) versus pre-confirmed `fields`. It also states negative scope: 'Does NOT compute rNPV. Not an autonomous verdict,' which prevents misuse.

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