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

Annotations declare mutation safety profile (readOnly=false, destructive=false, idempotent=false). Description adds critical behavioral context not in annotations: credit cost model, asynchronous polling pattern, prerequisite data state (CV parsing), and temporal dependency chain (poll until completed). 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?

Five sentences covering: (1) core action + cost, (2) return value, (3) polling workflow with specific tool names, (4) ID sourcing prerequisites, (5) data state prerequisites. Zero redundancy; front-loaded with essential action; each sentence advances the agent's understanding of how to invoke and manage the async workflow.

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 complex async operation with no output schema, description comprehensively covers the complete lifecycle: initiation → polling → results retrieval. Addresses hidden complexity including credit costs, data prerequisites, and tool dependencies. Sufficient for an agent to correctly orchestrate the full batch workflow without additional documentation.

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 67% (analysis_type lacks description). Description adds semantic value by specifying sourcing for the two required parameters (context_id from atlas_list_contexts, candidate_ids from atlas_list_candidates), which is crucial for correct invocation. Does not compensate for missing analysis_type description, but schema enums provide partial coverage.

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?

Description states specific verb (Start) + resource (batch GEM analysis) + scope (across multiple candidates). Explicitly distinguishes from single-candidate sibling atlas_start_gem_analysis by emphasizing 'batch' and 'multiple candidates', and distinguishes from other batch operations by specifying 'GEM analysis'.

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?

Provides explicit workflow: returns job_id → poll with atlas_get_batch_gem_status → fetch results with atlas_get_batch_gem_results. Names specific prerequisite tools (atlas_list_contexts, atlas_list_candidates) and data state requirements (CVs must be fully parsed). Includes cost disclosure (10 credits per candidate) for economic decision-making.

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