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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the tool is safe and idempotent. The description adds value by detailing the report's contents (e.g., appeal outcomes, ratings, PACT-Act pathways) and its non-predictive, educational nature. This goes beyond what annotations provide.

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 extremely concise—three well-structured sentences. It front-loads the core action ('return a full corpus-grounded report'), lists key report elements, and ends with a disclaimer. Every sentence adds value without 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?

Given the tool's complexity, the description adequately covers inputs, output contents, and qualification (educational). The output schema exists to define return structure, so that gap is acceptable. It does not mention error handling or edge cases, but overall it gives a clear picture of what the agent will get.

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?

Both parameters have schema descriptions (condition as slug/alias, example_limit with default/min/max). The tool description adds context by explaining how example_limit relates to 'a few representative decisions' and reinforces condition input flexibility. Schema coverage is sufficient, and the description clarifies usage beyond the schema.

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 returns a 'full corpus-grounded report' for a single condition, listing specific components (appeal outcomes, service-connection theories, ratings, etc.). It uses verbs like 'return' and distinguishes this comprehensive tool from siblings like 'list_conditions', 'search_bva_decisions', and 'get_corpus_stats' by calling it 'the richest single call' for condition queries.

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 positions this as the primary tool for broad condition overviews ('The richest single call...'). It specifies the input format (slug or alias) and clarifies the output is educational, not predictive. However, it does not explicitly state when to avoid this tool or name sibling alternatives, leaving some implicit guidance.

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