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

Beyond the readOnly/openWorld/idempotent annotations, the description reveals meaningful behavior: text input triggers extraction and marks inputs_unconfirmed, each claim is grounded or marked insufficient_evidence, and a meta block includes versioning. It explicitly denies computing rNPV and being an autonomous verdict, adding substantial behavioral transparency.

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?

The description is only three sentences but packs in purpose, input modes, output components, and exclusions. It is front-loaded with the core purpose and every sentence adds necessary information with no redundancy.

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 a nested fields object and a rich output schema (present though not shown), the description still covers input constraints, output composition, and limitations. It fully prepares the agent for correct invocation without needing to infer missing details.

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 parameter names are documented, but the description adds key semantics: text triggers extraction and marks inputs_unconfirmed, while fields are 'pre-confirmed' (implying trusted input). This clarifies the practical difference between the two params beyond the schema's type descriptions.

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?

The description clearly states it produces a 'transparent, provenance-linked CONDITIONAL READ on a drug asset for deal triage,' specifying the verb, resource, and context. It also lists concrete outputs (reasoning chain, flags, metrics, meta) and exclusions (does NOT compute rNPV), making it distinct from sibling tools like get_dossier and query_landscape.

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?

The description provides explicit input-mode guidance: 'Pass either text (machine-extracted, inputs_unconfirmed) or pre-confirmed fields.' It also sets context ('for deal triage') and notes what it does not do, which indirectly helps a user pick a different tool if needed, though it does not name specific alternatives.

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