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

With annotations already declaring readOnly/idempotent/non-destructive, the description adds substantial behavioral context: it enumerates return contents (38 CFR criteria, CAVC excerpts with docket number, relevance score), explains per-source limiting, and describes the empty-corpus fallback behavior. It also clarifies that docket numbers come only from returned results, a non-obvious constraint.

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 dense but every sentence delivers value: usage trigger, return contents, precedent status, limit behavior, empty-corpus fallback, and caveats. It's front-loaded with the 'Use this when' hook, making it scannable. No filler or 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?

For a search tool with no output schema, the description fully covers what to expect: it lists result categories (38 CFR criteria, CAVC decisions with identifiers, statutory standards), explains the limit behavior, and addresses edge cases like empty corpus. It also properly scopes the tool's role (not reading claims, not legal advice), making it complete for agent 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 coverage is 100%, so baseline is 3. The description goes beyond the schema by noting the limit parameter 'caps results per source' (adding per-source nuance) and implying diagnosticCode filtering via 'searched by keyword or diagnostic code.' It does not redefine the parameters but adds meaningful context for interpreting results.

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 purpose: 'Use this when a question calls for the text of a VA rating regulation or for case law, searched by keyword or diagnostic code.' It specifies the resources (regulations, CAVC decisions) and distinguishes from siblings like calculate_combined_rating or lookup_compensation_rate, which address numeric calculations rather than legal text.

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 opens with explicit 'when to use' guidance and provides a clear exclusion: 'It does not read an individual claim and it is not legal advice.' It also explains that CAVC decisions are binding precedent, helping the agent understand relevance. Though no sibling alternative is named, the unique scope makes such exclusion unnecessary.

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