Assess Target Druggability

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

Well beyond the annotations (readOnly/idempotent/openWorld), the description discloses the data sources per signal (ChEMBL, Open Targets, AF2 pLDDT, gnomAD LOEUF) and explicitly delimits their interpretation — pLDDT is 'not binding evidence' and LOEUF is 'not toxicity evidence.' It also flags the score as author-defined and uncalibrated. It stops short of describing behavior under missing/partial signal data or any latency/caching traits.

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?

Front-loaded with the purpose and output taxonomy, then a numbered breakdown that maps one-to-one onto the four signals, closing with the caveat. Slightly verbose with bold formatting and some redundancy between 'author-defined' and 'uncalibrated,' but nearly every line carries 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?

An output schema exists, so return structure needn't be explained, and annotations cover the safety profile. The description conveys the scoring inputs and their epistemic limits. The remaining gap is operational: no statement about how partial or missing signal coverage is handled, which matters for a composite score with open-world lookups.

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 at the top-level params object is 0% (only a nested object is documented), so the description must carry weight. The mention of 'approved drugs + clinical compounds' implicitly maps to include_clinical_stage, but the description never addresses the params wrapper or the UniProt accession requirement, leaving the inner schema to do the work.

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 ('druggability assessment for a protein target') and immediately names the output artifact (HOT/WARM/COLD/NOT_DRUGGABLE). The enumeration of the four integrated signals distinguishes it from single-signal siblings such as analyze_structural_confidence or score_binding_pocket_geometry.

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?

Usage is implied by the framing as the integrative/composite scorer and by the caution that it is 'not a validated predictive model, clinical safety result.' However, it never explicitly states when to call this versus running the individual siblings, nor any prerequisites such as data availability for all four signals.

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