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

With no annotations provided, the description carries the full burden. It transparently discloses that the tool only reads cached predictions, does not compute new ones, and returns cached=false with a note if nothing is cached. It also lists the return fields (best binding core, %Rank_EL, binder level, %Rank_Neo). This goes beyond simple schema information and sets correct expectations.

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 three concise sentences. The first sentence front-loads the core purpose, the second details the return values and behavior, and the third clarifies the limitation and alternative. Every sentence contributes valuable information with no redundancy or filler.

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 simple lookup tool with two well-documented parameters and no output schema, the description covers the essential context: what the tool does, what it returns, its limitation (cached only), and the fallback behavior when no cache exists. It also provides an alternative for new predictions. This is complete for the tool's complexity.

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 input schema already provides 100% coverage with descriptions and examples for both parameters (allele and peptide). The description mentions the parameters but adds no new semantic detail beyond 'peptide + HLA allele'. Per the rubric, baseline 3 is appropriate when schema_coverage is high.

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's function: 'Look up a CACHED MHC-I binding prediction for a peptide + HLA allele.' It uses a specific verb ('look up'), identifies the resource (MHC-I binding prediction), and explicitly scopes to cached data. This clearly distinguishes it from siblings which are generic database/search tools.

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 explicit usage guidance: it notes that this tool does NOT run new predictions and only reads cached ones, and directs users to an alternative ('interactive button on the mutation page of the website') for generating new predictions. This is a clear when-to-use vs. when-not-to-use with an explicit alternative.

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