lookup

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

No annotations are supplied, so the description carries the burden — and it does disclose the response modality ('returns text', 'draws nothing') plus the upstream data sources behind each topic (PubChem, ChEBI, UniProt, KEGG), which tells the agent where facts come from and why coverage varies. It does not mention failure behavior for unknown compounds, caching, or rate limits, which keeps it out of the top band.

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-loaded with the one-line purpose, then a scannable bulleted topic list, then exclusions — a logical order that lets an agent stop reading early once it has what it needs. It is slightly longer than necessary; the 'see the list above' pointer in Args and the repeated default restate information already given in the bullets.

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?

For a two-parameter read tool with an output schema already documenting return values, the description covers everything else an agent needs: which topic yields which class of facts, the naming convention for input, and the boundaries against three overlapping sibling tools. Nothing required to invoke it correctly 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 description coverage is 0%, so the description must compensate and does: every `topic` enum value is defined with the exact facts it returns, and the practical use case for at least two ('safety' for lab protocols, 'physical' for experimental values) is spelled out. The `name` parameter gains a hard constraint absent from the schema — English/IUPAC names only, with concrete contrastive examples ('Aspirin' not 'Acetylsalicylsäure').

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 a specific verb and resource — 'Fetch a specific fact or value about a compound as plain text' — and immediately clarifies the output modality. It explicitly separates itself from three siblings (generate_molecule for bare names, lookup_molecule_data for visual data sheets, predict_spectrum for derived spectra), so an agent can route correctly without opening a schema.

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?

Gives both directions: a positive trigger ('when the request asks for a named piece of data') and three explicit exclusions each paired with the alternative tool to use instead. The default topic and the 'Not this tool for' block remove nearly all ambiguity about when to select it.

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