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

Annotations only cover the safety profile (readOnly, idempotent, closed-world), yet the description goes well beyond them, enumerating returned sections (developers/partners/licensors, targets, mechanism, modality, indications with stage and backing trial, lifespan evidence, news) and disclosing a plan-based access tier where non-entitled accounts 'read an outline'. With no output schema, this is exactly the behavioral context the agent needs.

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?

Two sentences, front-loaded with the usage trigger before the payload description. The long enumeration of returned fields is dense but each item earns its place given the absence of an output schema; the plan-tier sentence is slightly tangential but genuinely useful.

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?

For a single-parameter read tool with no output schema, the description covers when to call it, what the key accepts, what is returned, and even how entitlements affect response depth. Nothing material is missing for correct invocation.

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% and the schema already says 'the asset's key or a code name', so the baseline is 3. The description adds real value by showing that multiple alias forms are accepted (ubx1325, UBX-1325, BMS-986278), clarifying that the agent need not normalize code names first.

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 ('get one drug or therapy programme') and scopes it to retrieval by name or code name. An agent can distinguish it from list_assets (enumeration) and get_entity (generic entity lookup) without opening any 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?

The opening clause 'Use this when the user asks about one drug or therapy programme by its name or any code name' gives an explicit trigger condition plus concrete alias examples. It stops short of naming alternatives (e.g. 'use list_assets to browse'), so it is clear context without explicit exclusions.

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