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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), so the bar is lower. The description adds genuine provenance context — curated experimental data from papers with PubMed IDs, explicitly not a prediction — which helps the agent trust and cite results, though it says nothing about response size or rate limits.

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-loads what is returned, then its authority, then how to call it. Three sentences with little waste, though the closing instruction to 'pass one or more UniProt accessions' partially repeats what the schema already states.

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 no output schema, the description carries the burden of explaining returns and does so well: affinity types, units, and the accompanying PubMed ID. Minor gaps like pagination or default ordering are covered by the schema, so nothing critical is missing.

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%, so the schema already documents limit, cutoff, and uniprot fully, including sort order and response-size implications. The description only restates that one or more accessions should be passed and gives an example (P24941 for CDK2), adding marginal value over the 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?

States a specific verb+resource: returns measured binding affinities (Ki, Kd, IC50, EC50 in nM) for ligands against a UniProt target, including the PubMed ID source. The input key 'uniprot' implicitly separates it from bindingdb_by_pdb and bindingdb_targets_by_smiles, but those siblings are never named, so differentiation is left to inference.

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 usage context: 'AUTHORITATIVE for what compounds bind this protein and how tightly' and contrasts it with prediction/web-summary tools ('this is experimental medicinal-chemistry data, not a prediction'). However, it names no alternatives and gives no explicit when-not guidance relative to the other bindingdb tools.

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