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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the description's extra value is real: it discloses the sort order (furthest stage first) and the plan-dependent behavior where some accounts read only an outline rather than full records. It does not discuss rate limits or error behavior, so not quite a 5.

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?

It is front-loaded with the usage trigger and then layers output contents, filter dimensions, and sibling routing in a logical order. It is dense and long, but nearly every clause carries distinct information; only slight compression is possible.

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 11 optional parameters, no output schema, and no annotations gaps, the description compensates well: it enumerates the fields returned per asset (developers, partners, code names, modality, targets, mechanism, indications with per-indication stage, hallmarks, lifespan evidence) and the ordering, plus it points to get_asset for full detail.

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 100%, so the baseline is 3. The description groups the filter dimensions (target, mechanism words, modality, hallmark, indication, stage, country, organisation, name) into a readable narrative, but it adds little syntax or semantics beyond what the schema already documents for each parameter.

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 names a specific verb and resource (lists drug and therapy programmes/assets) and states exactly what each record contains. It explicitly distinguishes itself from get_asset ('read one in full') and count_pipeline ('count them'), so an agent can route without opening a 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?

It opens with the user intent that should trigger it ('which drugs or therapies are in development against a target... who develops them and how far each has got') and names both alternatives with their distinct jobs. When-to-use and sibling routing are fully explicit.

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