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

Beyond the annotations (readOnly, non-destructive, closed-world), the description discloses the internal preprocessing (reactants joined, compounds canonicalised, each side sorted), the confidence semantics (product of product-atom attention scores), and an honesty caveat that the result is a prediction rather than a measurement. This adds real behavioral context; only permission/rate-limit style details are absent.

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?

Four sentences, front-loaded with the action and resource, and each sentence carries information (engine, preprocessing, output shape, caveat). The benchmarking citation is slightly decorative but justifies the accuracy claim.

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 read-only prediction tool with a full parameter schema and an output schema, the definition is complete: it explains what is computed, how inputs are normalised, and how to read the confidence value. The only minor gap is any mention of the _subject/_files reference parameters.

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 100%, so the 'reaction' parameter and the library-reference parameters are already documented. The description contributes the useful nuance that descriptors/atom ordering are normalised and that existing maps are ignored, but this is marginal beyond the schema and the _subject/_files plumbing goes unmentioned.

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 precise verb+resource ('Predict which reactant atom each product atom came from') and names the technique (atom-to-atom mapping) plus the specific engine (RXNMapper). An agent can immediately tell this apart from sibling tools like enumerate_reaction or compare_molecules.

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?

Usage is implied rather than stated: the tool is for reactions needing atom mapping, and the caveat 'A prediction, not a measurement' hints at when its output should be trusted. However, there is no explicit when-to-use/when-not or naming of an alternative mapping approach, so guidance stays at the implied level.

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