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

Annotations already declare read-only, idempotent, non-destructive. The description adds value by specifying case-insensitive matching, return fields (ids, names, cancer types, sample counts), and noting 'Keyless, open data' (no authentication needed). No contradictions with annotations.

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?

Three sentences are efficient and front-loaded with the core action. Every sentence adds distinct value (action, matching behavior, return fields, access info). No redundant or filler content.

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?

Despite lacking an output schema, the description explains return fields and data sources. For a simple search tool with two optional parameters, the description provides all necessary context for an AI agent to understand behavior and output.

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?

All parameters are fully described in the input schema (100% coverage). The description adds minimal extra semantics: it rephrases query matching and notes case-insensitivity, but does not detail the limit parameter. Schema coverage carries the burden, so baseline 3 is appropriate.

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 specifies the action (search), resource (public cancer genomics studies), and scope (cBioPortal sources like TCGA, CPTAC, MSK). It distinguishes from siblings like get_study (single study) and list_cancer_types (list only) by focusing on keyword matching across multiple fields.

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 implies usage for searching studies by keyword, but does not explicitly exclude other tools or provide when-not-to-use guidance. Sibling tools like deep_research or validate_claim are not mentioned, leaving some ambiguity about alternatives.

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