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

Annotations already declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint. The description adds value by enumerating specific returned properties (band gap, formation energy, crystal structure, etc.) and confirming the data source (Materials Project, 150K+ materials), which goes beyond what annotations provide.

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 description is a single paragraph that efficiently conveys purpose, example, returned properties, and data scope. It is front-loaded with the core action, but the list of properties could be slightly more structured (e.g., bulleted). Every sentence adds value.

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 the tool's complexity (returns many computed properties) and the existence of an output schema, the description adequately covers what the agent can expect. The list of property types is comprehensive, and the mention of database cross-references adds helpful context.

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 only parameter 'material_id' has full schema coverage (100%). The description adds meaning by providing an example format and explicitly stating that IDs can be obtained from the sibling tool 'science.materials.search', which helps the agent understand how to source valid inputs.

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 clearly states the tool retrieves DFT-computed properties for a material using a specific Materials Project ID, with an example (mp-149 for silicon). It distinguishes from sibling tools like 'science.materials.elasticity' and implies using 'science.materials.search' to obtain IDs.

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?

The description specifies when to use (when full computed properties are needed for a known material ID) and lists returned properties, but does not explicitly state when not to use or provide alternatives beyond the mention of materials.search for ID lookup.

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