spectral_custom

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

With no annotations, the description fully discloses behavioral traits: security (no eval, recursive-descent parser), supported operations (arithmetic, parentheses, numeric literals, band variables), and limitations (no function calls or arbitrary code).

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, well-structured paragraph that front-loads the purpose, provides a clear example, and explains security. Every sentence adds value with no redundancy.

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?

The description covers purpose, security, syntax, and example. However, it lacks mention of error handling (e.g., invalid expression or missing bands) and the return value, which are minor omissions for a custom math tool.

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% with descriptions for both parameters. The description adds a concrete example and explains the parser's safety, going beyond the schema by clarifying the expression syntax and security model.

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 'Evaluate a custom band math expression using a safe expression parser.' It specifies the verb (evaluate), the resource (custom band math expression), and distinguishes from sibling spectral index tools like spectral_ndvi by emphasizing custom expressions.

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 provides an example and explains supported operations, but does not explicitly state when to use this tool versus the specific spectral index tools (e.g., spectral_ndvi). It implies usage for custom indices not covered by siblings.

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