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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds contextual details beyond these: it states 'no auth required' and describes the data coverage (18,500+ targets from 650+ organisms) and licensing. It also clarifies the return fields, which aligns with read-only behavior. No contradictions with annotations.

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 four sentences long, each adding meaningful information: purpose, return fields, downstream usage, and data source/licensing. It is front-loaded with the primary function and avoids fluff or redundant phrasing. The structure is efficient and well-organized.

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 an output schema present, the description does not need to detail return value structure. It covers the essential aspects: what the tool does, how to use it (including optional parameters), what it returns, how to chain it with a sibling tool, and the data source and licensing. There are no missing pieces for an agent to invoke 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?

The schema has 100% coverage for all parameters, so the baseline is 3. The description adds value by providing concrete examples for query ('Acetylcholinesterase', 'Epidermal growth factor receptor', 'COX-2') and organism ('Homo sapiens', 'Rattus norvegicus', 'Escherichia coli'), and explains that omitting query browses with other filters. These examples and usage notes go beyond the schema's basic 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 the verb 'Search' with a specific resource (biological drug targets in the ChEMBL database) and enumerates the categories (proteins, enzymes, receptors, ion channels). It also distinguishes itself from sibling tools by explicitly directing users to chembl.activity.bioactivity for downstream compound retrieval, which clarifies its scope relative to other ChEMBL tools.

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 explains how to use the tool: search by name, target type, and organism, and notes that omitting query allows browsing with other filters. It also mentions the downstream use of the returned target_chembl_id with chembl.activity.bioactivity. It does not explicitly state when not to use it or compare with chembl.molecules.search, but the guidance is clear enough for most scenarios.

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