annotate_cell_types

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the agent knows this is a write operation. The description adds the preprocessing prerequisite for reference methods, which is useful context, but doesn't describe what data gets modified (e.g., adding cell type labels) or other side effects.

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 appropriately short and front-loaded with the main action. The Args section is minimal and the note is useful. It would benefit from a bit more structure, but it's concise and readable.

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?

This is a complex tool with many methods and parameters, an output schema, and a destructive flag. The description only covers the basic purpose and one prerequisite. It doesn't explain method-specific requirements (cellassign needs marker_genes, singler uses celldex), parameter interactions, or the expected outcome. Given the complexity, this is insufficient for correct invocation.

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 0% per context, so the description must compensate. It only lists example parameter names (method, reference_data_id, cell_type_key) without explaining their meaning or constraints. The nested params schema has many fields, but the description barely scratches the surface, leaving the agent to infer semantics from field names.

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 action and resource: 'Annotate cell types in spatial transcriptomics data.' This is a specific verb+resource combination that distinguishes it from sibling tools like analyze_cnv or find_spatial_genes.

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 a usage prerequisite: reference methods (tangram, scanvi) require reference_data_id to be preprocessed. However, it doesn't explicitly state when to use this tool versus alternatives or when not to use it, so guidance is only partial.

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