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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, covering safety and side effects. The description adds useful context: it lists all returned fields, names the source (EMBL-EBI ChEMBL), notes the CC BY-SA 3.0 license, and explicitly states no auth is required. This goes beyond the structured annotations without contradicting them.

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 three sentences plus a source line, front-loading the core purpose and returns. It avoids redundancy and each sentence contributes value (search capabilities, returned fields, phase guidance, source/auth). The inclusion of database size and publication count is slightly promotional but still useful for trust. No wasted words.

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?

Given the presence of a full output schema and safety annotations, the description is complete: it covers what the tool searches, what filters are typical, what fields are returned, and the data source/auth requirements. It doesn't need to explain return structure or safety. The only minor gap is no explicit relationship to sibling tools, but that is not required for calling it correctly.

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?

With 100% schema description coverage, the baseline is 3. The description adds some framing (e.g., 'drug molecules and bioactive compounds') and restates phase filtering, but most of the parameter meaning is already in the schema (e.g., max_phase=4 means approved). It does not introduce novel parameter semantics beyond what the schema already provides.

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 states a specific action ('Search the ChEMBL database') and the exact search dimensions (name, clinical phase, molecular type). It also enumerates the returned properties, making the tool's scope unambiguous. While it doesn't explicitly name sibling tools, the verb 'search' and the filter categories clearly distinguish it from chembl.molecules.detail, chembl.activity.bioactivity, and chembl.targets.search.

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 provides clear context for when to use the tool: searching molecules by name, phase, or type, with practical examples like 'max_phase=4 for approved drugs' and 'max_phase_gte=3 for late-stage candidates.' However, it does not explicitly state when not to use it or mention alternative tools (e.g., chembl.molecules.detail for a known ID), so it stops short of a full 5.

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