pubchem-mcp-server

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

Annotations declare readOnly/idempotent/openWorld; description adds valuable behavioral context beyond these flags: 'Efficiently batches' signals performance optimization, and noting that includeDescription/includeClassification 'adds one API call per CID' warns about latency/cost implications. 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?

Information-dense single sentence (or compound sentence) with zero fluff. Front-loaded with core purpose ('Get detailed compound information by CID'), followed by parenthetical elaboration of return values, and closes with operational constraint ('Efficiently batches up to 100 CIDs'). Every clause serves selection or invocation guidance.

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 high schema coverage, presence of output schema, and rich annotations, the description achieves completeness by mapping parameter flags to real-world data categories (pharmacology, therapeutic use, FDA classes). It appropriately delegates return value specifics to the output schema while providing sufficient high-level orientation.

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% with detailed field descriptions. Description adds semantic grouping (e.g., categorizing the 25+ property options into 'physicochemical properties', explaining that drug-likeness covers 'Lipinski/Veber rules'), which helps the agent understand intent and content boundaries beyond the mechanical schema.

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?

Opens with specific verb-resource 'Get detailed compound information by CID' and comprehensively enumerates return categories (physicochemical properties, textual description, synonyms, drug-likeness, pharmacological classification). The mention of 'batches up to 100 CIDs' clearly distinguishes this from single-lookup or search-oriented siblings.

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?

Provides clear context through detailed feature enumeration (e.g., specific properties like XLogP, TPSA, Lipinski rules), implicitly distinguishing it from siblings like get_compound_image or get_bioactivity. Lacks explicit 'when not to use' or prerequisite guidance (e.g., doesn't mention that CIDs must be obtained via search_compounds first), but the scope is precisely delineated.

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