Get Binding Sites

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description adds substantial behavior beyond that: it filters crystallization artifacts (glycerol, PEG, sulfate), classifies sites by type, and reports per-site druggability and modality recommendations with concrete thresholds. This is exactly the kind of non-obvious processing behavior an agent needs.

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 map statement is front-loaded, followed by method, output contents, and usage in a logical order with efficient bullet lists. It is somewhat long relative to a one-parameter tool, but nearly every sentence adds decision-relevant 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?

Given an output schema exists, the description need not enumerate return values, yet it usefully previews site classification and druggability outputs. Combined with the guidance on which IDs to pass and the multi-structure strategy, an agent has everything required 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 single parameter (pdb_id) has 0% schema description coverage, so the description must carry the load. It does so partially by establishing that the argument is a specific PDB ID obtained from GetRelatedStructures, which clarifies the expected value provenance, though it gives no format example or validity constraints.

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 verb and resource ('Map all known binding sites in a protein structure') and even specifies the method (analyzing non-polymer entities from co-crystallized ligands). It is clearly distinct from data-fetching siblings like GetRelatedStructures, though it never explicitly contrasts itself with ConsolidateBindingSites, so it stops short of full sibling differentiation.

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 gives clear context: call this on specific PDB IDs surfaced by GetRelatedStructures, and for comprehensive coverage call it across multiple structures with different ligands. That names the upstream tool and the multi-call strategy, but there is no explicit 'do not use this when...' exclusion versus ConsolidateBindingSites.

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